© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 145554
    Prev
    Next
    INDEX
    Explanations

    The Basic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     đèn
    0.72
    昏
    0.71
     marbled
    0.70
     existed
    0.70
     확률
    0.68
    бов
    0.68
    垃圾
    0.68
    кие
    0.68
    ək
    0.68
     Marguerite
    0.68
    POSITIVE LOGITS
     Сы
    0.81
     estime
    0.79
    ruitment
    0.77
     reckoned
    0.75
     che
    0.75
    䧉
    0.75
    App
    0.74
    ości
    0.74
    ونس
    0.74
    Վ
    0.73
    Activations Density 0.000%

    No Known Activations