© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8349
    Prev
    Next
    INDEX
    Explanations

    reading file lines

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

    reading and converting data

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    filename
    0.57
    檔
    0.54
    文件名
    0.53
    Filename
    0.52
     filename
    0.52
    的文件
    0.51
     fileName
    0.49
    档
    0.48
    파일명
    0.47
    FileName
    0.47
    POSITIVE LOGITS
    readline
    0.75
    readlines
    0.75
     readline
    0.72
     read
    0.67
     lines
    0.65
     contents
    0.63
     Lines
    0.63
     LINES
    0.63
     líneas
    0.63
    Lines
    0.61
    Activations Density 0.004%

    No Known Activations