© 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. 34-GEMMASCOPE-RES-131K
    7. 75632
    Prev
    Next
    INDEX
    Explanations

    wig and Whig party

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

    The neuron activates on any word containing the substring “wig.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    pung
    -0.89
     thal
    -0.85
    houettes
    -0.82
     banheiro
    -0.80
    ѐ
    -0.79
     herói
    -0.78
     planejamento
    -0.78
    ULATION
    -0.78
     kanyang
    -0.77
    Goddess
    -0.75
    POSITIVE LOGITS
    Wig
    1.18
     Wig
    1.17
    wag
    1.00
     Wag
    0.99
     wiggle
    0.94
    Wag
    0.91
    wig
    0.91
     jig
    0.81
     wag
    0.81
    asaan
    0.80
    Activations Density 0.006%

    No Known Activations