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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118939
    Prev
    Next
    INDEX
    Explanations

    function call with arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    caden
    -0.84
     웹
    -0.83
     лечения
    -0.77
    Voor
    -0.76
     Leinwand
    -0.75
     violación
    -0.74
    多かった
    -0.74
     فرنسا
    -0.73
    Loch
    -0.73
     엔
    -0.73
    POSITIVE LOGITS
     call
    3.22
    call
    2.86
     calls
    2.27
    Call
    2.19
     apply
    2.13
    apply
    2.09
     Call
    2.06
    CALL
    1.98
     CALL
    1.92
    calls
    1.73
    Activations Density 0.019%

    No Known Activations