© 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. 5028
    Prev
    Next
    INDEX
    Explanations

    Chinese names and events

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

    wishing good fortune

    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
    literally
    0.52
    necessarily
    0.52
     جذاب
    0.46
    regulatory
    0.46
    specify
    0.45
    ليز
    0.44
    numerator
    0.44
    髖
    0.43
    뤽
    0.43
     noirâtres
    0.43
    POSITIVE LOGITS
     Weibo
    0.89
     Xiao
    0.85
     Jiang
    0.84
     Qing
    0.80
     Yuan
    0.79
     netizens
    0.79
     Qiu
    0.79
     Dao
    0.77
     Xiang
    0.77
     Miao
    0.76
    Activations Density 0.106%

    No Known Activations