© 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. 44573
    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
     this
    -1.75
     which
    -1.52
     kepada
    -1.45
    to
    -1.44
     that
    -1.42
    d
    -1.28
     being
    -1.25
    頃は
    -1.20
     and
    -1.16
     cittadini
    -1.16
    POSITIVE LOGITS
     intently
    1.28
    zdroj
    1.22
    เช่น
    1.21
    viendo
    1.20
     Púb
    1.20
    quisa
    1.20
    ִּ
    1.20
    reordered
    1.20
     votre
    1.19
    ческом
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.