© 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. 7463
    Prev
    Next
    INDEX
    Explanations

    where things happen

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     in
    -1.52
     it
    -1.37
    dci
    -1.18
     there
    -1.17
    ꈍ
    -1.16
     by
    -1.08
    czegóły
    -1.05
     oldukça
    -1.05
     другую
    -1.04
     tampoco
    -1.03
    POSITIVE LOGITS
    chede
    1.37
     از
    1.35
     diğer
    1.28
    tians
    1.27
    хождения
    1.26
    migrationBuilder
    1.22
    setof
    1.22
     Projektu
    1.21
     menghadapi
    1.21
     essendo
    1.20
    Activations Density 0.026%

    No Known Activations