© 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. 2654
    Prev
    Next
    INDEX
    Explanations

    mixed and summarized concepts

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

    提问，机，春，网

    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
    雖然
    0.98
    能夠
    0.95
    鰱
    0.92
    獲得
    0.91
    錯誤
    0.90
    蟶
    0.89
    價格
    0.89
    獼
    0.87
    勝利
    0.87
    已經
    0.86
    POSITIVE LOGITS
    址
    0.89
    情的
    0.82
    密的
    0.75
    龄
    0.71
    意的
    0.68
    々
    0.68
    身的
    0.67
    定的
    0.66
    发的
    0.64
    粹
    0.64
    Activations Density 0.015%

    No Known Activations