© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3867
    Prev
    Next
    INDEX
    Explanations

    punctuation and common 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_16_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
    il
    0.38
     這個
    0.38
    on
    0.35
     创建
    0.35
     這
    0.35
     这个
    0.34
     Madera
    0.34
     定义
    0.34
     適
    0.34
     給
    0.33
    POSITIVE LOGITS
    大
    0.32
    人
    0.32
    를
    0.32
    ۰
    0.31
     are
    0.31
    ق
    0.31
    گ
    0.30
    را
    0.30
    斯
    0.29
    پ
    0.29
    Activations Density 2.647%

    No Known Activations