© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16648
    Prev
    Next
    INDEX
    Explanations

    China, hope, security, decided

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

    China geopolitical and economic news

    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_31_width_262k_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
    鲔
    0.77
    莳
    0.73
    ็ม
    0.71
    癃
    0.68
    膑
    0.68
    沩
    0.67
    泷
    0.66
    蚬
    0.65
    畯
    0.65
    辂
    0.64
    POSITIVE LOGITS
     Xinhua
    0.69
    mentioned
    0.60
    zhong
    0.59
    umumkan
    0.58
     yuan
    0.57
    name
    0.55
    xiang
    0.55
    text
    0.54
    hij
    0.54
     Chinese
    0.54
    Activations Density 0.027%

    No Known Activations