© 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. 87010
    Prev
    Next
    INDEX
    Explanations

    complete details about

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

    school, can, control, for

    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
     عالی
    0.56
     ㅣ
    0.55
     없다
    0.53
     سازی
    0.53
     меры
    0.53
    ᓵ
    0.52
     کتاب
    0.52
     밤
    0.51
     наре
    0.51
     endearing
    0.51
    POSITIVE LOGITS
    1
    0.50
    k
    0.48
    hr
    0.48
    kv
    0.46
    ď
    0.46
    cr
    0.45
    yr
    0.45
    Ｆ
    0.45
    人口
    0.44
    kr
    0.44
    Activations Density 0.001%

    No Known Activations