© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129612
    Prev
    Next
    INDEX
    Explanations

    puck, Huck, Rourke, Puckett

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

    The neuron fires on any token containing the letter sequence “uck” (e.g. puckering, Puckett, Huckabee).

    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
    _
    -3.88
    1
    -3.50
    ༐
    -2.58
    ”(
    -2.56
    ”-
    -2.50
    -“
    -2.44
    基本的
    -2.41
    re
    -2.39
    之前的
    -2.38
    ...”
    -2.36
    POSITIVE LOGITS
    鼱
    2.97
     pylori
    2.75
    ########.
    2.72
    鷙
    2.70
    鉏
    2.69
    鱨
    2.53
    可以选择
    2.52
    ೣ
    2.48
    ৳
    2.48
    '
    2.48
    Activations Density 0.003%

    No Known Activations