© 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. 82662
    Prev
    Next
    INDEX
    Explanations

    . Since the

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

    orchestrator, Manhattan, entities, upgrade

    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
    Negative Logits
    –
    0.51
    纲
    0.47
     day
    0.47
    on
    0.46
    ї
    0.45
    avers
    0.44
     Corbin
    0.44
     ounce
    0.44
    识别
    0.43
    -
    0.43
    POSITIVE LOGITS
     مراکز
    0.54
     دولت
    0.53
     کر
    0.51
    رفت
    0.50
     ด
    0.50
     مکان
    0.50
     enviados
    0.49
     مادر
    0.48
    OpportunitiesBy
    0.48
     زنان
    0.48
    Activations Density 0.000%

    No Known Activations