© 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. 415
    Prev
    Next
    INDEX
    Explanations

    s/S at start of words

    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
    初始化
    0.37
    㡷
    0.33
    谜
    0.32
    μβρίου
    0.32
    리티
    0.32
    电流
    0.31
    嚆
    0.31
    віду
    0.31
    ждён
    0.30
    用戶
    0.30
    POSITIVE LOGITS
     S
    0.76
     s
    0.58
    S
    0.54
     الس
    0.51
     së
    0.50
     স
    0.47
     س
    0.46
    ucceeded
    0.46
     ס
    0.44
     स
    0.42
    Activations Density 0.271%

    No Known Activations