© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62493
    Prev
    Next
    INDEX
    Explanations

    temporary files or directories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     نا
    -0.85
    ්‍
    -0.78
    ural
    -0.75
    мий
    -0.73
     subpo
    -0.73
    bath
    -0.73
    ̍
    -0.70
    ⡄
    -0.69
     ergän
    -0.69
     supernatural
    -0.69
    POSITIVE LOGITS
    rpt
    0.84
     hawk
    0.81
     Оте
    0.79
    置いて
    0.79
     poquito
    0.79
    temporary
    0.77
    思い
    0.77
    Ⓔ
    0.77
    ERC
    0.76
     TEM
    0.75
    Activations Density 0.008%

    No Known Activations