© 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. 71231
    Prev
    Next
    INDEX
    Explanations

    licensing entirely, Toronto paramedics, Navajo neighbors

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

    the concept of distinguishing

    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
    Negative Logits
    ת
    0.56
    ี
    0.56
    ปี
    0.54
    JSON
    0.50
     ব্যতীত
    0.48
    พัน
    0.47
    Year
    0.46
    IPA
    0.46
    ED
    0.46
    :
    0.46
    POSITIVE LOGITS
     unwitting
    0.50
     glorify
    0.50
     chuva
    0.49
     muestras
    0.48
     hordes
    0.48
     predicament
    0.47
     productores
    0.46
    ामान्य
    0.45
     ordinairement
    0.45
     Eliza
    0.45
    Activations Density 0.001%

    No Known Activations