© 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. 16046
    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
     INTERESAR
    -1.14
     before
    -1.07
     from
    -1.07
    éte
    -1.04
     what
    -1.04
    λές
    -1.03
    팬
    -1.02
     ауди
    -1.00
     one
    -0.98
     Latinoamérica
    -0.98
    POSITIVE LOGITS
     
    1.08
     aberto
    1.04
     geleg
    0.96
    这些
    0.96
    ‘
    0.94
    stringValue
    0.92
    Nl
    0.91
    ero
    0.91
    1
    0.91
     francès
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.