© 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. 128916
    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
    All
    -1.24
     through
    -1.20
    ：</
    -1.19
    Not
    -1.19
     both
    -1.19
     Both
    -1.17
    Both
    -1.16
    t
    -1.14
     =
    -1.13
     using
    -1.10
    POSITIVE LOGITS
     who
    1.52
     obuv
    1.50
    cartão
    1.39
     mármol
    1.30
     krás
    1.29
     nieuwe
    1.28
     šed
    1.27
     luxus
    1.27
     histó
    1.27
     dáms
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.