© 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. 129636
    Prev
    Next
    INDEX
    Explanations

    year, Q, or, rating, spots

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

    page alive, transaction commit

    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
    getActiveSheet
    0.48
    ิ
    0.48
     அரை
    0.46
     конца
    0.46
     千
    0.46
    あとは
    0.46
     متح
    0.45
    擎
    0.45
     progressivement
    0.45
    ︵
    0.44
    POSITIVE LOGITS
    asting
    0.45
    C
    0.45
    NC
    0.45
    ya
    0.44
    IN
    0.43
    B
    0.42
    By
    0.42
    allocated
    0.42
     eqs
    0.42
    人不
    0.41
    Activations Density 0.000%

    No Known Activations