© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 69744
    Prev
    Next
    INDEX
    Explanations

    work and workers

    np_acts-logits-general · gemini-2.5-flash-lite

    warning texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perasaan
    0.49
    ,|
    0.46
     merasakan
    0.45
     intoxicated
    0.44
    вин
    0.44
     exquisitely
    0.44
    пе
    0.43
    ский
    0.43
    зо
    0.43
    窒
    0.43
    POSITIVE LOGITS
     효율
    0.50
     worker
    0.49
    imerk
    0.46
    렙
    0.46
     जरूरी
    0.45
     Worker
    0.44
     പ്രവർ
    0.44
     Fail
    0.43
     मजदूरों
    0.43
    IL
    0.43
    Activations Density 0.001%

    No Known Activations