© 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. 207277
    Prev
    Next
    INDEX
    Explanations

    prior notice

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

    qualifiers or degrees

    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
    ダル
    0.48
    緒
    0.48
    規則
    0.47
    護
    0.47
    例外
    0.47
    詩
    0.47
    鎗
    0.47
    ゴミ
    0.46
    똥
    0.46
    活動
    0.46
    POSITIVE LOGITS
     can
    0.58
     may
    0.54
    ،
    0.52
     wasn
    0.50
     moulds
    0.50
     Prepar
    0.48
     ،
    0.47
     might
    0.46
     Crop
    0.46
     και
    0.46
    Activations Density 0.000%

    No Known Activations