© 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. 82983
    Prev
    Next
    INDEX
    Explanations

    foreign language or academic terms

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

    positive indications or outcomes

    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
    imètre
    0.53
     北海道
    0.49
     甘
    0.48
    <unused1007>
    0.46
     可愛
    0.46
     ブルー
    0.45
     保存
    0.45
     アド
    0.45
     sodass
    0.45
     防止
    0.45
    POSITIVE LOGITS
    财经
    0.53
     sectoral
    0.47
     counterpart
    0.47
     கல்விய
    0.47
     राज
    0.45
     asignatura
    0.44
    қ
    0.44
     fungsi
    0.43
     bijvoorbeeld
    0.43
     parametr
    0.43
    Activations Density 0.002%

    No Known Activations