© 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. 92101
    Prev
    Next
    INDEX
    Explanations

    callable and closure

    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
     يون
    -0.78
    Gregory
    -0.77
    "}";
    -0.75
    дру
    -0.73
    corrected
    -0.72
    サラダ
    -0.70
    orges
    -0.70
     lót
    -0.69
    correct
    -0.68
     Gregory
    -0.68
    POSITIVE LOGITS
     callable
    3.41
    callable
    2.95
    Callable
    2.61
     Callable
    2.55
     closure
    2.47
     Closure
    2.36
    isFunction
    2.23
     closures
    2.14
    Closure
    2.13
    closure
    2.11
    Activations Density 0.085%

    No Known Activations