© 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. 10-GEMMASCOPE-RES-131K
    7. 8466
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ;
    -1.12
    .}(
    -1.11
    About
    -1.10
    thodox
    -1.09
    withstanding
    -1.08
    On
    -1.07
     gemeinsame
    -1.05
    Only
    -1.05
    Just
    -1.04
    сро
    -1.03
    POSITIVE LOGITS
    坚决
    1.00
     favoritas
    1.00
     erhi
    0.99
     reeks
    0.97
     metody
    0.96
    ריים
    0.96
     bellissimo
    0.95
     iglesias
    0.94
    FUENTES
    0.94
     pokaz
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.