© 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. 10-GEMMASCOPE-RES-131K
    7. 100497
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵↵
    -1.70
     if
    -1.69
     AND
    -1.64
    {
    -1.63
     Then
    -1.63
     Thus
    -1.62
     or
    -1.59
     =
    -1.55
     щодо
    -1.52
     This
    -1.50
    POSITIVE LOGITS
     arme
    1.87
     toques
    1.80
     rente
    1.80
     etui
    1.78
     炖
    1.75
     remun
    1.71
     notori
    1.70
     brevet
    1.69
     niedersachsen
    1.68
     posibil
    1.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.