© 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. 72591
    Prev
    Next
    INDEX
    Explanations

    referring to drawings or figures

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

    resources, however

    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
    왼
    0.57
    ラ
    0.54
    −
    0.50
    원
    0.50
    ノー
    0.50
    urid
    0.49
    산
    0.47
    写真
    0.46
    金
    0.46
    Conte
    0.46
    POSITIVE LOGITS
     Glasses
    0.48
     ሁሉም
    0.46
    द्वी
    0.45
     Policing
    0.45
     tooling
    0.44
     গণহত্যার
    0.44
    嚧
    0.44
     Daughters
    0.43
     Sewing
    0.43
     disillusioned
    0.43
    Activations Density 0.000%

    No Known Activations