© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 66143
    Prev
    Next
    INDEX
    Explanations

    time is not linear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dominance
    0.41
     बातों
    0.40
     Grail
    0.40
     Моск
    0.39
    蜊
    0.37
     Stoff
    0.36
     flame
    0.36
    schild
    0.36
     Сі
    0.36
     method
    0.35
    POSITIVE LOGITS
     crooked
    0.86
     skewed
    0.81
     mismatched
    0.77
     misalignment
    0.77
     uneven
    0.74
     lệch
    0.73
     messed
    0.71
    乱
    0.71
     неправи
    0.70
     misplaced
    0.69
    Activations Density 0.000%

    No Known Activations