© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2209
    Prev
    Next
    INDEX
    Explanations

    game, play, styles, limerick, gremlin, satchel, YMCA, porno, phophogypsum, nanites, Colosseum, monads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    банк
    0.99
    ت
    0.87
    roc
    0.85
    urs
    0.82
    antina
    0.79
    utzerklärung
    0.79
    ｂ
    0.78
    ıy
    0.77
    yb
    0.77
    b
    0.77
    POSITIVE LOGITS
     Freestyle
    1.62
     Doodle
    1.54
     Indian
    1.45
     Singh
    1.45
     Syndicate
    1.43
     Game
    1.43
     little
    1.42
     Play
    1.41
     game
    1.40
     hobby
    1.38
    Activations Density 0.070%

    No Known Activations