© 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. 73027
    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
    EMIA
    -0.94
     besi
    -0.91
    лізу
    -0.90
     suci
    -0.89
     yng
    -0.87
     syk
    -0.86
     kata
    -0.86
     madu
    -0.86
    whatever
    -0.85
     noma
    -0.85
    POSITIVE LOGITS
     nuevamente
    1.20
    有り
    1.05
     (!__
    1.05
     erneut
    1.04
    (!__
    0.99
    ();
    0.97
     sustancias
    0.95
     ponownie
    0.93
     Etiquette
    0.92
     zufrieden
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.