© 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. 10-GEMMASCOPE-RES-131K
    7. 43157
    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
    provides
    -1.25
     étudier
    -1.08
    
    -1.05
    
    -1.04
    naturally
    -1.04
     chantier
    -1.04
     differentiates
    -1.02
     fournir
    -1.01
    튿
    -1.00
     réservoir
    -0.99
    POSITIVE LOGITS
     not
    1.16
     seamlessly
    1.00
    [
    0.99
     {
    0.98
     Maybe
    0.97
     Why
    0.94
     Really
    0.93
    {
    0.92
     Anyway
    0.91
     their
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.