© 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. 114316
    Prev
    Next
    INDEX
    Explanations

    local directories and organizations

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

    Monitoring and metrics

    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
    Κ
    0.59
    Yosh
    0.57
    時間
    0.55
    Би
    0.55
    时间
    0.54
    ل
    0.53
    بان
    0.52
    Კ
    0.52
    पो
    0.51
    بو
    0.51
    POSITIVE LOGITS
    .
    0.63
     supposed
    0.54
     reproduce
    0.48
     NOAA
    0.48
     failed
    0.46
     society
    0.46
     fulfill
    0.46
     utilitarian
    0.46
     grand
    0.45
     universitaire
    0.45
    Activations Density 0.001%

    No Known Activations