© 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. 196290
    Prev
    Next
    INDEX
    Explanations

    Sunday

    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
     =~
    0.37
     acompanha
    0.37
     किशोर
    0.36
    чень
    0.35
    뭄
    0.35
    ளே
    0.35
    哺
    0.34
     drivetrain
    0.34
    ফ
    0.34
     modelo
    0.34
    POSITIVE LOGITS
     Sunday
    1.91
    Sunday
    1.86
     sunday
    1.73
     Sundays
    1.70
    sunday
    1.63
     रविवार
    1.60
    रविवार
    1.49
     zond
    1.42
     domingo
    1.39
     dimanche
    1.39
    Activations Density 0.000%

    No Known Activations