© 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. 15390
    Prev
    Next
    INDEX
    Explanations

    code prefixes and their continuations

    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_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
     Reifen
    -1.20
     tilbake
    -1.11
     herv
    -1.09
     ferien
    -1.08
     Beton
    -1.04
    ⁾
    -1.03
    лару
    -1.02
     in
    -1.01
     memainkan
    -1.01
     what
    -0.99
    POSITIVE LOGITS
     dianteiro
    1.27
     tijdens
    1.13
     ouvido
    1.09
     współpracy
    1.06
     traseiro
    1.00
    (),"
    0.98
    úsqueda
    0.97
    广大
    0.95
    Formik
    0.95
    byshev
    0.95
    Activations Density 0.004%

    No Known Activations