© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60712
    Prev
    Next
    INDEX
    Explanations

    dimension and identifiers

    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
    鬭
    -3.53
    gucig
    -3.25
    кроссовки
    -3.23
     odeur
    -3.16
     ristoranti
    -3.09
     leggero
    -3.06
     eccellente
    -2.98
     utente
    -2.97
    棡
    -2.92
     icône
    -2.91
    POSITIVE LOGITS
      
    3.38
    .
    3.19
     (
    3.09
     &
    3.05
    ↵
    3.00
    {
    3.00
     -
    2.83
    <em>
    2.83
     /
    2.81
    m
    2.72
    Activations Density 0.002%

    No Known Activations