© 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. 71443
    Prev
    Next
    INDEX
    Explanations

    new ways, creation of, blown back, Government makes, levels vary

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

    refer

    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
    ﻫ
    0.61
    АТ
    0.54
    ЕН
    0.53
    дан
    0.50
    ვნ
    0.50
    ЕД
    0.50
    ешься
    0.49
    ભાવ
    0.48
    ﻪ
    0.48
    SERVICIO
    0.48
    POSITIVE LOGITS
     American
    0.52
     volcanic
    0.47
     lacks
    0.46
     Japanese
    0.46
     Australian
    0.46
     European
    0.46
     অন্যান্য
    0.46
     COVID
    0.46
     möglicherweise
    0.46
     protruding
    0.45
    Activations Density 0.001%

    No Known Activations