© 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. 4944
    Prev
    Next
    INDEX
    Explanations

    kanji or katakana

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

    special characters and Chinese

    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
    Introdu
    0.55
    則是
    0.52
    ের
    0.50
     refreshments
    0.46
    崠
    0.46
    之間
    0.46
    ᱭ
    0.46
    𝑅
    0.46
    畯
    0.46
    Bathroom
    0.46
    POSITIVE LOGITS
     背景
    0.54
     让
    0.53
     심
    0.50
     현
    0.50
     사
    0.46
     편
    0.46
     noi
    0.44
     流
    0.43
    偏
    0.43
     죄
    0.43
    Activations Density 0.004%

    No Known Activations