© 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. 103634
    Prev
    Next
    INDEX
    Explanations

    where clauses

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

    where: leads to explanation

    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
     ശേഷം
    0.51
     则
    0.49
     wodurch
    0.48
     meisten
    0.47
    ()){
    0.46
     പരിശോധ
    0.45
     riesce
    0.45
     ဆို
    0.44
     determina
    0.44
     लिहाजा
    0.44
    POSITIVE LOGITS
    ：
    0.53
    这是
    0.47
    0.46
    一个是
    0.44
    :
    0.44
    ,
    0.43
    posto
    0.41
    Component
    0.41
    Base
    0.40
    作为
    0.40
    Activations Density 0.008%

    No Known Activations