© 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. 43248
    Prev
    Next
    INDEX
    Explanations

    this foreign

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

    culprits, lot, function, sequence

    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
    エス
    0.47
    об
    0.47
    サン
    0.46
     "").
    0.46
    卧
    0.44
    origin
    0.42
     данном
    0.42
    ტერ
    0.42
    원본파일명
    0.42
    鹏
    0.41
    POSITIVE LOGITS
    的時間
    0.46
     sampai
    0.45
     इथे
    0.45
     Safer
    0.45
    -{\
    0.44
     Almost
    0.43
    urably
    0.42
     Sudah
    0.42
    veillance
    0.42
    𝖆
    0.42
    Activations Density 0.000%

    No Known Activations