© 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. 110032
    Prev
    Next
    INDEX
    Explanations

    obtain human, night accommodation, persuasive essay

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

    scale, organizations, milestone

    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
    提供了
    0.49
    ждён
    0.49
    ブン
    0.47
    墅
    0.45
     których
    0.45
    %，
    0.45
    已
    0.44
    完成了
    0.43
    疇
    0.43
    跳转
    0.43
    POSITIVE LOGITS
     AAC
    0.49
     AA
    0.48
     också
    0.48
     atypical
    0.48
    aal
    0.47
     ”
    0.47
     A
    0.47
    an
    0.46
    aid
    0.46
    aas
    0.45
    Activations Density 0.001%

    No Known Activations