© 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. 12529
    Prev
    Next
    INDEX
    Explanations

    import * as

    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
    t
    3.02
    to
    2.96
    tion
    2.87
    deki
    2.42
    los
    2.29
    lle
    2.29
    the
    2.28
    c
    2.23
    ly
    2.21
    tions
    2.13
    POSITIVE LOGITS
    enment
    1.75
     цвета
    1.72
    inescent
    1.68
    ̫
    1.66
     humanity
    1.66
     writings
    1.62
     elaboración
    1.62
    igné
    1.62
     renamed
    1.61
    अन्य
    1.61
    Activations Density 0.001%

    No Known Activations