© 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. 117996
    Prev
    Next
    INDEX
    Explanations

    providing savings, prepared to, pieces, returns

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

    foreign characters

    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
    ต
    0.51
     sensation
    0.47
    چہ
    0.46
    пта
    0.45
     argomento
    0.45
     orchestration
    0.44
     suivent
    0.44
     nanti
    0.44
    禊
    0.44
    зайн
    0.43
    POSITIVE LOGITS
     भौ
    0.54
     牛
    0.54
    وک
    0.47
     ठंड
    0.46
    onov
    0.46
     கூ
    0.45
     而且
    0.44
    ruvic
    0.44
     Chiu
    0.43
    鼕
    0.43
    Activations Density 0.001%

    No Known Activations