© 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. 39662
    Prev
    Next
    INDEX
    Explanations

    cookbook or recipe book

    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
    </em>
    -2.77
     They
    -2.20
     \
    -2.03
    </td>
    -1.95
    warnai
    -1.93
     \\
    -1.92
     $
    -1.91
     */
    -1.91
     สำหรับ
    -1.80
     viaj
    -1.77
    POSITIVE LOGITS
    u
    2.84
    as
    2.53
    to
    2.48
    ↵↵
    2.39
     ?
    2.30
    —“
    2.28
    .”
    2.16
    眼的
    2.14
    </h1>
    2.13
     soo
    2.11
    Activations Density 0.002%

    No Known Activations