© 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. 186844
    Prev
    Next
    INDEX
    Explanations

    complete set, maximum of, one family

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

    lmsys.org URLs

    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
    naio
    0.48
    icos
    0.45
    ol
    0.44
    ียบ
    0.44
    繧
    0.43
    にか
    0.42
    ICO
    0.42
    менение
    0.42
    sterreich
    0.42
    OLS
    0.42
    POSITIVE LOGITS
    这个
    0.51
     બાબ
    0.51
     этой
    0.51
    这
    0.50
     الجدول
    0.50
     এই
    0.49
     गाड़ी
    0.48
    乐队
    0.48
     식으로
    0.46
    ేశారు
    0.46
    Activations Density 0.001%

    No Known Activations