© 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. 33598
    Prev
    Next
    INDEX
    Explanations

    google links and publications

    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
     if
    -1.20
     faſt
    -1.17
    Ț
    -1.10
     anything
    -1.09
    ються
    -1.09
    glichen
    -1.07
     kohta
    -1.05
    ctivo
    -1.04
    '];
    -0.99
    ：[
    -0.98
    POSITIVE LOGITS
     assorted
    1.11
     этих
    1.01
    attva
    0.97
     preocupaciones
    0.97
     respectivos
    0.95
     corriendo
    0.93
     thôi
    0.92
    Betyg
    0.91
     cuyo
    0.91
     amenazas
    0.91
    Activations Density 0.003%

    No Known Activations