© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185780
    Prev
    Next
    INDEX
    Explanations

    website, applied

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

    CV structure

    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
     serait
    0.49
    ثیر
    0.48
     sepd
    0.47
    ویر
    0.47
    钮
    0.47
    زیز
    0.47
    لې
    0.45
    の両
    0.44
    ثر
    0.44
    ریب
    0.44
    POSITIVE LOGITS
     숙
    0.50
    ringa
    0.49
     अक्सर
    0.48
     EVA
    0.48
     संरक्षक
    0.48
    naire
    0.46
     गंग
    0.46
    killing
    0.45
     салы
    0.45
    ante
    0.43
    Activations Density 0.001%

    No Known Activations