© 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. 108624
    Prev
    Next
    INDEX
    Explanations

    formatting tags

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

    types

    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
    兔
    0.49
    дзі
    0.44
    лле
    0.42
    стом
    0.42
    -'].
    0.41
    뚠
    0.41
     بع
    0.41
    MktCap
    0.40
    녠
    0.40
    ద్రా
    0.40
    POSITIVE LOGITS
     ‘’
    0.46
    rdquo
    0.42
     क्वालिटी
    0.41
     kejadian
    0.41
     Types
    0.40
     tipos
    0.40
    emark
    0.39
     konuda
    0.39
     gerçekten
    0.39
     ব্যাপারে
    0.38
    Activations Density 0.000%

    No Known Activations