© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1495
    Prev
    Next
    INDEX
    Explanations

    Chinese Pinyin with tones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    乸
    0.63
    蚋
    0.59
    鲔
    0.59
     blanchâtre
    0.58
    媜
    0.58
    銥
    0.57
    膂
    0.57
    銠
    0.56
    愊
    0.56
    Раз
    0.55
    POSITIVE LOGITS
     Xiao
    0.76
     Liao
    0.75
     Xia
    0.75
     Zhong
    0.75
     Jiang
    0.74
     Yuan
    0.71
     Zhang
    0.70
     Zheng
    0.70
     Qing
    0.70
     Jia
    0.68
    Activations Density 0.030%

    No Known Activations