© 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. 32989
    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
    -2.08
     my
    -1.48
     until
    -1.42
    !
    -1.38
     only
    -1.38
     begin
    -1.34
     their
    -1.34
     just
    -1.34
     (
    -1.32
    resave
    -1.32
    POSITIVE LOGITS
    pulseira
    1.77
    Procedimento
    1.54
    Informazioni
    1.51
     meninos
    1.47
     Многие
    1.46
    Dettagli
    1.43
     acolo
    1.41
    有一定
    1.41
    cticut
    1.39
     装饰
    1.38
    Activations Density 0.000%

    No Known Activations