© 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. 12275
    Prev
    Next
    INDEX
    Explanations

    Warner Bros

    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
     rousing
    2.73
    湃
    2.43
    𝙸
    2.41
    AIM
    2.34
    ப்போதும்
    2.31
    ηση
    2.30
    số
    2.24
    GEORGE
    2.23
    㓡
    2.23
    ۢ
    2.23
    POSITIVE LOGITS
    ن
    2.71
    ல்
    2.48
    べく
    2.44
    क
    2.36
    م
    2.28
     самом
    2.19
     ocasión
    2.16
     able
    2.14
    ला
    2.14
     doubt
    2.12
    Activations Density 0.002%

    No Known Activations