# Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model

arXiv: https://arxiv.org/abs/2607.20058 · HTML: https://mlsanity.com/paper/2607.20058/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 55 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions](https://mlsanity.com/paper/1901.01753/) (2019)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)
- [Verbalizable Representations Form a Global Workspace in Language Models](https://mlsanity.com/paper/2607.15495/) (2026)
- [ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning](https://mlsanity.com/paper/2402.04268/) (2024)
- [Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models](https://mlsanity.com/paper/2310.14491/) (2023)
- [MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalities](https://mlsanity.com/paper/2310.10445/) (2023)
- [AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise](https://mlsanity.com/paper/2507.00310/) (2025)
- [BioinspiredLLM: Conversational Large Language Model for the Mechanics of Biological and Bio-inspired Materials](https://mlsanity.com/paper/2309.08788/) (2023)
- [MeLM, a generative pretrained language modeling framework that solves forward and inverse mechanics problems](https://mlsanity.com/paper/2306.17525/) (2023)
- [LLM-Prop: Predicting Physical And Electronic Properties Of Crystalline Solids From Their Text Descriptions](https://mlsanity.com/paper/2310.14029/) (2023)
- [Accelerating Scientific Discovery with Generative Knowledge Extraction, Graph-Based Representation, and Multimodal Intelligent Graph Reasoning](https://mlsanity.com/paper/2403.11996/) (2024)
- [PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking](https://mlsanity.com/paper/2410.12375/) (2024)
- [Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange](https://mlsanity.com/paper/2603.14312/) (2026)
- [BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning](https://mlsanity.com/paper/2603.04124/) (2026)
- [Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination](https://mlsanity.com/paper/2607.00924/) (2026)
- [MaterialBENCH: Evaluating College-Level Materials Science Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2409.03161/) (2024)

## Built on by (most cited first, 1 of 1)

- [Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models](https://mlsanity.com/paper/2610.19696/) (2026)

## Abstract (arXiv)

Large language models can answer scientific questions, yet a correct output does not reveal whether the model represents or uses the governing physics. Here, using three open-weight Gemma 4 models (google/gemma-4-E4B-it, google/gemma-4-12B-it, google/gemma-4-31B-it) we identify three experimentally separable signatures of materials-science mechanism information: selective concept readability, relational encoding of qualitative constitutive orientation, and causal, context-dependent control of constrained engineering answers. We combine matched direct and Jacobian vocabulary readouts, option-free state geometry, a 60-law counterfactual benchmark and causal interventions. In 50 held-out materials descriptions, three independently fitted Jacobian lenses reproduced concept ranks, and target-free word sets from both readouts enabled blinded identification of 9 of 10 mechanism families. A separate 72-prompt benchmark produced mechanism-specific hidden-state neighborhoods, but an exact graph audit showed that this apparent physical organization was equally explained by numerical comparison. We therefore compared otherwise identical prompts in which only the direction of the physical input was reversed, asking whether the resulting hidden-state movement followed the supplied constitutive law. These state transformations ordered direct, physically neutral and inverse laws across 60 frozen relations and correctly oriented 39 of 40 directional laws, whereas lexical controls were near chance. Bidirectional interventions shifted answer probabilities toward or away from the physically appropriate outcome across all 12 matched cases, while counterfactual state patches transferred opposing decision signals across mechanisms and answer formats. Physical relationships were therefore more visible in controlled state changes than in absolute states alone.