© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31368
    Prev
    Next
    INDEX
    Explanations

    java package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     кушымта
    0.47
     앱
    0.47
    ⬯
    0.46
    PlayerDataCache
    0.46
    实验
    0.45
    𒉈
    0.45
     computational
    0.45
     модуль
    0.45
     automaton
    0.45
    UnitTest
    0.45
    POSITIVE LOGITS
    i
    0.64
    to
    0.62
    in
    0.61
    u
    0.59
    as
    0.58
    ik
    0.55
    si
    0.55
    o
    0.55
    ini
    0.54
    ia
    0.53
    Activations Density 0.002%

    No Known Activations