© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58793
    Prev
    Next
    INDEX
    Explanations

    allosteric conformational changes

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects technical terms related to protein structure and conformational changes, particularly focusing on allosteric mechanisms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IAC
    -0.85
    atar
    -0.82
     GUIDELINES
    -0.79
    Labs
    -0.77
     RICHARD
    -0.75
     Fiore
    -0.74
     Galli
    -0.74
    chris
    -0.74
    douard
    -0.73
     necessità
    -0.73
    POSITIVE LOGITS
     conformational
    1.55
    Conform
    1.51
     Conform
    1.45
     motions
    1.27
     conformation
    1.22
    conform
    1.18
     changes
    1.13
     conform
    1.10
     motion
    1.09
     change
    1.08
    Activations Density 0.240%

    No Known Activations