© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152831
    Prev
    Next
    INDEX
    Explanations

    Who's Who Legal

    np_acts-logits-general · gemini-2.5-flash-lite

    important, crucial, polite, hopeful, appearing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    s
    0.63
    leetcode
    0.50
    sexual
    0.45
     ziehen
    0.44
     国内
    0.44
    拉
    0.43
     भयानक
    0.42
    方程式
    0.42
    kilomet
    0.41
    Polygon
    0.41
    POSITIVE LOGITS
    䥑
    0.45
     ઓફ
    0.45
    পুন
    0.45
    श्री
    0.44
    чена
    0.44
    佽
    0.44
    ologiche
    0.43
    鏟
    0.43
     elegante
    0.43
    ુંદર
    0.43
    Activations Density 0.001%

    No Known Activations