© 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. 15518
    Prev
    Next
    INDEX
    Explanations

    parameters min and max

    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
     in
    -1.02
     motorola
    -0.95
    駐車場
    -0.91
    лил
    -0.90
    =?";
    -0.90
     Vz
    -0.90
    ət
    -0.89
     повин
    -0.89
     vulnerables
    -0.86
    VersionUID
    -0.84
    POSITIVE LOGITS
    λυ
    1.02
     conceivable
    0.93
     ouver
    0.93
     отече
    0.93
     шка
    0.92
     min
    0.90
     integer
    0.90
     max
    0.90
     consejo
    0.90
     évidemment
    0.89
    Activations Density 0.006%

    No Known Activations