© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71876
    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
     in
    -1.41
    groet
    -1.24
    porsche
    -1.21
     kovo
    -1.18
    ğını
    -1.18
     from
    -1.15
     únicas
    -1.15
    の為
    -1.13
     truly
    -1.13
     unique
    -1.13
    POSITIVE LOGITS
     perché
    1.16
    IRS
    1.14
    zką
    1.13
    例文帳に追加
    1.12
     беременности
    1.10
    fordshire
    1.09
    rsquo
    1.09
    ۔
    1.09
    el
    1.06
     ™
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.