© 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. 152794
    Prev
    Next
    INDEX
    Explanations

    specific things followed by context

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

    non-English 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
     dispensing
    0.53
    ;
    0.53
    a
    0.52
    rines
    0.50
    :
    0.49
    Mason
    0.48
     dispute
    0.48
     formul
    0.47
     dispenser
    0.47
    ><
    0.46
    POSITIVE LOGITS
     число
    0.56
    ސް
    0.54
     Ска
    0.49
    تی
    0.49
     짧
    0.49
     SUPPL
    0.48
    بی
    0.47
     சுவாச
    0.47
    ド
    0.46
    ಕ್
    0.46
    Activations Density 0.001%

    No Known Activations