© 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. 15013
    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
     in
    -1.09
     on
    -1.06
     with
    -1.04
     like
    -1.01
     your
    -0.99
     (
    -0.99
     for
    -0.98
     by
    -0.95
    +"&
    -0.95
    -
    -0.94
    POSITIVE LOGITS
    IZONTAL
    1.03
    🧖
    1.00
     fragte
    1.00
    fting
    0.97
    commodation
    0.96
    ⌧
    0.96
    VPS
    0.95
    Dacă
    0.94
    ſt
    0.94
    bergement
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.