© 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. 147419
    Prev
    Next
    INDEX
    Explanations

    upholstery, Bighorn, history, coupons

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

    buffers, odd, friendly, evaluation

    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
     brainstorm
    0.45
    arina
    0.45
     thinker
    0.44
     altijd
    0.43
    ඊ
    0.42
     অস্থির
    0.42
     rotary
    0.42
    借り
    0.42
    ȧ
    0.41
    ães
    0.41
    POSITIVE LOGITS
    timestamp
    0.54
    paragraphs
    0.50
    populations
    0.50
    log
    0.46
     paragraphs
    0.46
    topo
    0.46
    paragraph
    0.45
    message
    0.45
    written
    0.44
    tops
    0.44
    Activations Density 0.001%

    No Known Activations