© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14759
    Prev
    Next
    INDEX
    Explanations

    Wick, Wiccan, Wicker, WiX

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

    The neuron fires on any token containing the letter‐sequence “wic” (case‐insensitive), as in “Wicket,” “Wiccan,” “Wiktionary,” “Smithwick,” etc.

    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
    _
    -2.42
    컫
    -2.19
    銥
    -2.19
     –>
    -2.17
    In
    -2.09
     financieros
    -2.08
     painstaking
    -2.08
    镔
    -2.05
    
    -2.02
     encompassing
    -1.97
    POSITIVE LOGITS
     '
    2.34
    archiwizowane
    2.13
    '
    1.77
     Jahren
    1.73
    她们
    1.70
     Selain
    1.69
     Risiko
    1.69
    鵙
    1.66
    a
    1.66
    蚡
    1.63
    Activations Density 0.003%

    No Known Activations