© 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. 30143
    Prev
    Next
    INDEX
    Explanations

    around the world

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

    penalty charge notice

    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
    usine
    0.42
     ಕೆಲವು
    0.39
    เมือง
    0.39
    檯
    0.39
    镇
    0.38
    ()(
    0.38
    راهيم
    0.38
     sappiamo
    0.38
     सिर
    0.38
     місто
    0.38
    POSITIVE LOGITS
     elong
    0.39
     Db
    0.39
     Panch
    0.38
     $('
    0.37
     Kond
    0.37
     đổ
    0.36
     Pard
    0.35
     $*
    0.35
     bounty
    0.35
     elongate
    0.35
    Activations Density 0.005%

    No Known Activations