© 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. 129797
    Prev
    Next
    INDEX
    Explanations

    Wilkinson, Atkinson, Walsh, Wilde

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

    The neuron fires on capitalized surnames ending in “kinson” (e.g. Wilkinson, Hopkinson).

    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
    ’
    -3.02
    l
    -2.91
    ⢊
    -2.64
     aching
    -2.55
    t
    -2.47
    .”
    -2.41
    i
    -2.39
    GRAPHICAL
    -2.38
    热水
    -2.33
    c
    -2.28
    POSITIVE LOGITS
     Hinsicht
    3.05
    "
    2.98
    .
    2.69
    ꔹ
    2.63
    桫
    2.34
     unmittel
    2.34
    医師
    2.28
    ی
    2.23
     Then
    2.23
     For
    2.23
    Activations Density 0.004%

    No Known Activations