© 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. 17703
    Prev
    Next
    INDEX
    Explanations

    Yang

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

    Yangtze, Yang, 阳, 洋

    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
     prefs
    0.38
     জৈন
    0.37
    vā
    0.37
    வியில்
    0.36
    HAD
    0.36
    얻
    0.35
    UIView
    0.35
    mongoUrl
    0.35
    newL
    0.34
    FLU
    0.34
    POSITIVE LOGITS
     양
    0.59
    Yang
    0.55
     Yang
    0.52
    痿
    0.50
    洋
    0.47
    柳
    0.47
    양
    0.47
    yang
    0.45
    lesias
    0.45
    楊
    0.44
    Activations Density 0.006%

    No Known Activations