© 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. 58457
    Prev
    Next
    INDEX
    Explanations

    Viewer

    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
    d
    -2.34
    }{
    -2.27
    など
    -2.22
    çok
    -2.05
    s
    -2.02
     was
    -2.02
    ar
    -1.98
    ⎘
    -1.95
    嗵
    -1.93
    る
    -1.89
    POSITIVE LOGITS
    </h3>
    2.83
     the
    2.52
    Eight
    2.20
    Each
    2.14
     تغذ
    2.13
     моя
    2.08
    ٞ
    2.06
     keben
    2.05
    By
    2.00
     hoher
    2.00
    Activations Density 0.003%

    No Known Activations