© 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. 185623
    Prev
    Next
    INDEX
    Explanations

    bumblebees, Thursday lunchtime, rehabilitation process

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

    specific nouns like Government, Revelation, Tuesday

    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
     Верхов
    0.52
     Сьогодні
    0.49
     Tạo
    0.49
    javaHome
    0.48
    쫀득
    0.48
     मौजूदा
    0.47
    דול
    0.47
    🧠
    0.47
    ProjectId
    0.47
     CtApp
    0.46
    POSITIVE LOGITS
    ວ
    0.49
     als
    0.46
    音
    0.45
    由
    0.44
    н
    0.43
    a
    0.42
    only
    0.42
    often
    0.42
    hereafter
    0.41
    S
    0.41
    Activations Density 0.000%

    No Known Activations