© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76986
    Prev
    Next
    INDEX
    Explanations

    result, STATUS, Bell

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

    This neuron fires on statement-terminating semicolons in code.

    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
    ;
    -1.17
    ;;
    -0.93
    編曲
    -0.87
    новения
    -0.83
    وقع
    -0.78
     as
    -0.77
     tangents
    -0.77
     parable
    -0.76
     лише
    -0.76
    教室
    -0.75
    POSITIVE LOGITS
    amental
    0.91
    кин
    0.90
    dă
    0.87
     jį
    0.85
    among
    0.85
     Chwiliwch
    0.84
     SOME
    0.83
    También
    0.80
    Advertise
    0.80
    Abend
    0.80
    Activations Density 0.002%

    No Known Activations