© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130519
    Prev
    Next
    INDEX
    Explanations

    points and dian

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

    The neuron selectively activates on the subword “dian” (in any context, e.g. “Dianping,” “dianion,” “dianhydride”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    i
    -2.22
    不
    -2.22
    ↵
    -2.14
    f
    -2.06
    b
    -2.06
    begin
    -1.98
    角色
    -1.94
     一个
    -1.86
    but
    -1.85
    The
    -1.78
    POSITIVE LOGITS
    鱨
    2.44
    赑
    2.38
    slut
    2.00
    葑
    1.95
    亖
    1.95
    鹛
    1.94
     تھے
    1.93
    genodigd
    1.92
    我这
    1.91
    趼
    1.91
    Activations Density 0.003%

    No Known Activations