© 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. 72594
    Prev
    Next
    INDEX
    Explanations

    dimensions and size

    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
    </h2>
    -1.84
     has
    -1.82
     have
    -1.55
     as
    -1.52
    ap
    -1.50
     o
    -1.45
    );
    -1.44
     грн
    -1.41
     if
    -1.38
     causado
    -1.38
    POSITIVE LOGITS
    
    1.72
    岽
    1.70
    ﾕ
    1.69
    xvii
    1.63
     marte
    1.63
    სქ
    1.59
     キーホルダー
    1.56
    転車
    1.56
     alarme
    1.56
    הגב
    1.55
    Activations Density 0.001%

    No Known Activations