© 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. 15670
    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
     Tiere
    -1.18
    档案馆
    -1.05
    LEAN
    -1.05
    isClosed
    -1.03
     Índice
    -1.00
    再去
    -0.99
    上げた
    -0.98
     бампер
    -0.98
    走去
    -0.96
    CLIP
    -0.96
    POSITIVE LOGITS
     that
    1.34
     such
    1.05
    swell
    0.99
     uitzicht
    0.98
     circunstancias
    0.94
    年齡
    0.94
     DISCUSS
    0.93
    鈥
    0.91
     and
    0.91
     or
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.