© 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. 9-GEMMASCOPE-2-RES-262K
    7. 12435
    Prev
    Next
    INDEX
    Explanations

    i-th words

    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_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dresser
    1.52
    ն
    1.51
    жи
    1.47
     साथ
    1.45
     ساتھ
    1.44
    ראל
    1.44
     благодаря
    1.43
    îtier
    1.43
     eikä
    1.42
     feud
    1.41
    POSITIVE LOGITS
    帼
    1.65
     ripples
    1.56
     bialgebras
    1.51
    ی
    1.47
     surjective
    1.44
    ্লিক
    1.44
     cationic
    1.42
    কাঠ
    1.40
     kaun
    1.40
     precincts
    1.40
    Activations Density 0.001%

    No Known Activations