© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 186
    Prev
    Next
    INDEX
    Explanations

    Chinese words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
    移除
    0.83
    下さい
    0.75
     Toutefois
    0.73
    髖
    0.72
    髋
    0.72
     बैंकिंग
    0.71
     يقوم
    0.70
     ガ
    0.70
     berfungsi
    0.70
     wesentlich
    0.69
    POSITIVE LOGITS
     viciss
    1.06
     incompar
    1.04
     domine
    1.03
     Qing
    0.99
     Atención
    0.95
     aristocratic
    0.95
     Xiao
    0.91
     netizens
    0.91
     cultivation
    0.91
     Qin
    0.90
    Activations Density 0.289%

    No Known Activations