© 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. 116764
    Prev
    Next
    INDEX
    Explanations

    protein surface and buried structures

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

    scientific and computational chemistry terminology related to molecular modeling and analysis.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on mentions of computational‐chemistry or molecular‐modeling method acronyms (e.g. MM/PBSA, CoMFA, QSAR, CoMSIA).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     чер
    -0.75
    nodeName
    -0.71
    ITER
    -0.69
    Conference
    -0.68
    Zn
    -0.68
    huriyet
    -0.68
     cerrada
    -0.68
     lå
    -0.67
    千里
    -0.66
    boh
    -0.66
    POSITIVE LOGITS
     solvent
    1.21
     buried
    1.15
     Solvent
    1.09
    Solvent
    1.04
     accessibility
    1.04
     Connolly
    0.93
     ASA
    0.91
     accessible
    0.91
     burying
    0.91
     Buried
    0.90
    Activations Density 0.073%

    No Known Activations