© 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. 30248
    Prev
    Next
    INDEX
    Explanations

    probability and statistics

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

    statistical measurements and distributions

    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
     अपडेट
    0.50
    uyết
    0.49
     Entwicklung
    0.48
     冖
    0.47
    枻
    0.45
     업데이트
    0.45
     обновление
    0.45
     середи
    0.45
    Aurora
    0.44
    绾
    0.44
    POSITIVE LOGITS
     random
    0.67
    random
    0.65
     mean
    0.61
     variability
    0.61
     distribution
    0.59
    mean
    0.58
     distributions
    0.57
     values
    0.54
    distribution
    0.54
     measurements
    0.54
    Activations Density 0.038%

    No Known Activations