© 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. 186809
    Prev
    Next
    INDEX
    Explanations

    the way we

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

    security and legal terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    з
    0.55
    тя
    0.54
    प्रधान
    0.53
    녈
    0.52
    ва
    0.51
     سلي
    0.50
    ன்
    0.49
    теля
    0.49
    ъз
    0.49
    భ
    0.49
    POSITIVE LOGITS
     পিছিয়ে
    0.49
    Charlie
    0.47
     weeding
    0.46
     wildest
    0.44
    Harvard
    0.44
    0.44
     brushed
    0.43
     grandson
    0.43
    usammen
    0.42
     Grandma
    0.42
    Activations Density 0.000%

    No Known Activations