© 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. 22-GEMMASCOPE-RES-131K
    7. 27646
    Prev
    Next
    INDEX
    Explanations

    foreign languages and terms

    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
     with
    -1.13
    F
    -0.98
     to
    -0.96
    L
    -0.95
    ED
    -0.94
     noticeable
    -0.92
    M
    -0.91
     Cremation
    -0.90
     בפ
    -0.88
    H
    -0.88
    POSITIVE LOGITS
     listes
    1.19
     befe
    1.05
     Máy
    1.01
    wered
    0.99
    lessed
    0.99
     sowieso
    0.97
     ajouter
    0.96
     vorige
    0.95
     Czę
    0.94
     beker
    0.94
    Activations Density 0.080%

    No Known Activations