© 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. 14549
    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
    tragung
    -1.09
     Durée
    -1.00
    ěř
    -1.00
     sebagainya
    -0.99
     lazos
    -0.98
     hvem
    -0.98
    sApp
    -0.98
    خول
    -0.97
    wwww
    -0.97
    wwwww
    -0.96
    POSITIVE LOGITS
     this
    1.09
     This
    1.06
     Это
    1.02
    大体
    0.98
     beholder
    0.96
    さんで
    0.95
    Propor
    0.93
     urg
    0.92
     blanches
    0.90
     هذا
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.