© 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. 26306
    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
    ltä
    -1.09
    婚礼
    -1.04
     from
    -0.96
     За
    -0.95
    ervé
    -0.95
    （※
    -0.94
     existir
    -0.94
    pá
    -0.94
    днев
    -0.93
     other
    -0.93
    POSITIVE LOGITS
    ant
    1.13
    ,,,
    1.10
    t
    1.05
    ,;
    1.05
    ru
    1.02
     gesammelt
    1.00
    ut
    0.98
    lords
    0.96
     scp
    0.96
    ,,,,
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.