© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86840
    Prev
    Next
    INDEX
    Explanations

    Wick, Wicca, wicket, Sick Children

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

    The neuron fires on any occurrence of the letter sequence “wic” (e.g. in “Wicket,” “Wiccan,” or “Wicket”).

    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
     soooo
    -2.89
    轳
    -2.83
     sooo
    -2.72
    沵
    -2.69
    comes
    -2.61
     to
    -2.59
     amd
    -2.53
     continually
    -2.52
    看他
    -2.48
     significantly
    -2.47
    POSITIVE LOGITS
     When
    3.91
    s
    3.53
    a
    2.94
    h
    2.80
    the
    2.80
     These
    2.67
    i
    2.61
    ↵
    2.58
    ),
    2.41
     Using
    2.39
    Activations Density 0.001%

    No Known Activations