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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17042
    Prev
    Next
    INDEX
    Explanations

    Gulp build tool

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

    gulp, build, minify

    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_53_width_65k_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
    ⚛
    0.42
    恢
    0.42
    驾驶
    0.41
     방정
    0.41
     확보
    0.39
    楨
    0.39
    SecurityCenter
    0.38
    类
    0.38
    殳
    0.38
    效应
    0.37
    POSITIVE LOGITS
     gulp
    1.41
    gulp
    1.37
     gul
    1.14
    gul
    0.97
    Gul
    0.95
    gulpfile
    0.90
     browserSync
    0.88
     Gul
    0.86
     गुल
    0.77
     pipes
    0.74
    Activations Density 0.002%

    No Known Activations