© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109810
    Prev
    Next
    INDEX
    Explanations

    programming loops and declarations

    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
     only
    -1.27
     with
    -1.02
    alnız
    -0.97
    
    -0.97
     something
    -0.97
     mostly
    -0.93
    нской
    -0.93
     for
    -0.93
    äft
    -0.92
     from
    -0.91
    POSITIVE LOGITS
    int
    1.64
     int
    1.25
    var
    1.18
    ;
    1.02
    ;</
    0.98
    let
    0.96
    register
    0.95
    ódź
    0.94
     spé
    0.93
    全都
    0.93
    Activations Density 0.003%

    No Known Activations