© 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. 99035
    Prev
    Next
    INDEX
    Explanations

    re- followed by a word

    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
    ↵↵
    -3.95
    .
    -3.88
    to
    -3.30
    ли
    -3.13
    te
    -3.03
    C
    -2.91
    m
    -2.91
    ON
    -2.73
     și
    -2.72
    <td>
    -2.61
    POSITIVE LOGITS
    ญี่ป
    3.11
    ruecos
    3.00
     parachoque
    2.91
    ୌ
    2.73
    ครื่อง
    2.73
    毉
    2.70
    ?"
    2.58
    ⢌
    2.56
     aching
    2.55
    Ꮏ
    2.55
    Activations Density 0.031%

    No Known Activations