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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5004
    Prev
    Next
    INDEX
    Explanations

    cleaning and cleaners

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

    cleaning and clean things

    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
    萸
    0.38
    跛
    0.38
     साकार
    0.37
    喁
    0.37
    ွဲ
    0.34
    မဲ့
    0.34
     المعادلات
    0.33
    刖
    0.33
    銜
    0.33
    輳
    0.33
    POSITIVE LOGITS
     cleaning
    4.50
     Cleaning
    4.28
    Cleaning
    4.28
    cleaning
    4.22
     cleaned
    4.09
     cleaners
    3.97
     limpieza
    3.97
     CLEAN
    3.95
    清洁
    3.94
     temiz
    3.94
    Activations Density 0.560%

    No Known Activations