© 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-262K
    7. 1180
    Prev
    Next
    INDEX
    Explanations

    驾驶员, 网络安全, 研究型, 民族主义, 债务证券

    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_262k_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
    蟶
    0.64
    癤
    0.60
    䳕
    0.58
    ਲੇ
    0.57
    比如說
    0.57
    綣
    0.56
    齙
    0.54
    釹
    0.54
    лі
    0.53
     劉
    0.52
    POSITIVE LOGITS
    的
    0.86
    信息
    0.70
    和
    0.66
    式
    0.65
    化
    0.64
    不同
    0.61
    工作
    0.60
    选择
    0.60
    程序
    0.60
    不
    0.60
    Activations Density 0.019%

    No Known Activations