© 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. 39228
    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
     and
    -1.22
    grafías
    -1.02
     then
    -1.00
    Другие
    -0.98
     Hoje
    -0.98
    futbolista
    -0.93
     Başkanı
    -0.92
     Outros
    -0.92
     that
    -0.91
    män
    -0.91
    POSITIVE LOGITS
    not
    0.93
     hielt
    0.91
    "
    0.88
     YET
    0.87
    xt
    0.87
    という
    0.85
    とか
    0.85
    0.84
     еще
    0.82
    Boca
    0.82
    Activations Density 0.000%
    No Known Activations
    This feature has no known activations.