© 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. 10-GEMMASCOPE-RES-131K
    7. 71620
    Prev
    Next
    INDEX
    Explanations

    function return void or unit

    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_10/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
     velg
    -2.17
     vermel
    -2.14
    
    -1.98
    瘰
    -1.92
     runde
    -1.91
     desmotiv
    -1.91
    戋
    -1.91
    蛲
    -1.90
    ఽ
    -1.88
     kram
    -1.87
    POSITIVE LOGITS
    .
    2.47
    <em>
    1.66
    ↵
    1.59
     –
    1.55
     on
    1.52
     However
    1.52
    Their
    1.49
    ,
    1.47
    <strong>
    1.46
     as
    1.46
    Activations Density 0.003%

    No Known Activations