© 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. 73080
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     and
    -1.20
     Belgian
    -1.00
     Israeli
    -0.97
    ⌗
    -0.97
     entrepreneurial
    -0.94
     ссылка
    -0.94
    ća
    -0.94
    riceps
    -0.94
     alumni
    -0.93
     Iranian
    -0.93
    POSITIVE LOGITS
     promesse
    1.06
     grizzly
    1.05
    athered
    1.02
     braw
    1.00
    她们
    1.00
     grunge
    1.00
    ḿ
    0.97
    但这
    0.95
    确实
    0.95
    ұл
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.