© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1107
    Prev
    Next
    INDEX
    Explanations

    notes and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     superfície
    0.48
    vVertex
    0.47
    र्जी
    0.46
    ’:
    0.46
     novela
    0.46
    را
    0.46
    يو
    0.45
    ’
    0.45
    naio
    0.45
     fün
    0.44
    POSITIVE LOGITS
    ↵
    0.56
     Notes
    0.46
    備考
    0.44
     Where
    0.43
     ارتباط
    0.43
    </th>
    0.42
     Corresponding
    0.42
     Note
    0.41
     イラスト
    0.41
     Перейти
    0.41
    Activations Density 0.042%

    No Known Activations