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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31409
    Prev
    Next
    INDEX
    Explanations

    legal, code, or event descriptions

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

    The neuron fires on code “include”/import‐style declarations and related tokens that bring in external modules or libraries (e.g. #include, import, require, using namespace, export default).

    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
    zwischen
    -0.85
    jno
    -0.73
     graphql
    -0.73
    Featured
    -0.70
     Verwaltungs
    -0.67
     Api
    -0.66
    unicode
    -0.65
     garaje
    -0.65
     historien
    -0.65
     Ked
    -0.65
    POSITIVE LOGITS
    νονται
    0.82
    LITERAL
    0.79
     grip
    0.79
     grips
    0.71
    acco
    0.71
    轩
    0.70
     frontier
    0.69
    
    0.69
    羡
    0.69
     דער
    0.68
    Activations Density 0.019%

    No Known Activations