© 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. 65660
    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
    вую
    -0.97
     Begins
    -0.97
    граф
    -0.94
     Վերցված
    -0.94
     its
    -0.93
    它们
    -0.93
    スズキ
    -0.91
    SIZES
    -0.91
    桌上
    -0.91
     you
    -0.91
    POSITIVE LOGITS
    lusconi
    0.95
     including
    0.94
     instead
    0.93
    expandafter
    0.91
     acestui
    0.91
     still
    0.90
     zamiast
    0.89
    beauty
    0.88
     мужская
    0.87
    diferentes
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.