© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48707
    Prev
    Next
    INDEX
    Explanations

    Korean particles and Japanese characters

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

    theoretical and speculative concepts

    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
     a
    0.66
     A
    0.61
     Coronado
    0.55
     the
    0.54
     J
    0.54
     R
    0.51
    ,
    0.50
    ;
    0.50
     Locking
    0.50
     Loco
    0.50
    POSITIVE LOGITS
    漢字
    0.52
    カスタム
    0.49
    Therates
    0.49
    ここでは
    0.49
    舉行
    0.49
    擔任
    0.48
    ۱۹
    0.47
    諡
    0.47
    眼鏡
    0.46
    顎
    0.46
    Activations Density 0.000%

    No Known Activations