© 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. 221181
    Prev
    Next
    INDEX
    Explanations

    as Assistant

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

    "ratio" or lists

    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
    নির্দিষ্ট
    0.52
    Сі
    0.50
     বয়সী
    0.49
     নিজের
    0.48
    প্তাহ
    0.48
    CCSD
    0.48
    ICKS
    0.47
     അദ്ദേ
    0.47
     instância
    0.47
    唪
    0.47
    POSITIVE LOGITS
     facsimile
    0.48
    za
    0.48
    m
    0.47
    N
    0.47
    al
    0.46
    arh
    0.45
     Tru
    0.45
    id
    0.44
    '
    0.44
     Of
    0.43
    Activations Density 0.000%

    No Known Activations