© 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. 22-GEMMASCOPE-RES-131K
    7. 16062
    Prev
    Next
    INDEX
    Explanations

    code examples and data

    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_22/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
     škola
    -0.97
     filmu
    -0.96
     škole
    -0.95
    television
    -0.94
     only
    -0.93
     Drž
    -0.90
    *}[
    -0.90
     without
    -0.88
     fær
    -0.88
     тільки
    -0.88
    POSITIVE LOGITS
     then
    0.99
    o
    0.98
    P
    0.91
     ´
    0.91
     selle
    0.90
    M
    0.88
    Ã
    0.87
    n
    0.86
    J
    0.86
    b
    0.85
    Activations Density 0.002%

    No Known Activations