© 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. 229382
    Prev
    Next
    INDEX
    Explanations

    accepts, tiling, week, wait, on, whipping

    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
    ت
    0.63
     Paese
    0.52
    జా
    0.50
     ميل
    0.50
    ות
    0.49
    钢琴
    0.49
     limites
    0.49
     Internationale
    0.48
     съем
    0.48
    篾
    0.48
    POSITIVE LOGITS
    rinth
    0.46
    boards
    0.45
     puzzles
    0.44
     menilai
    0.42
    autoplay
    0.42
    Boards
    0.42
    ctuaries
    0.41
    TComponent
    0.41
    Percy
    0.41
     menyatakan
    0.40
    Activations Density 0.000%

    No Known Activations