© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9734
    Prev
    Next
    INDEX
    Explanations

    wedding ceremony

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

    The neuron detects formal wedding-ceremony language—mentions of weddings, marriage, officiant duties (e.g. “married,” “wedding,” “license,” “I will,” “you will”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     학습
    0.73
     daily
    0.73
     updated
    0.72
     습
    0.71
    噬
    0.71
     промы
    0.70
     currentValue
    0.70
     hábitos
    0.69
     exploited
    0.67
     DAILY
    0.66
    POSITIVE LOGITS
    wedding
    1.92
     wedding
    1.85
     weddings
    1.74
    Wedding
    1.73
     Wedding
    1.72
    婚礼
    1.72
    👰
    1.69
     свадь
    1.66
     pernikahan
    1.63
     Weddings
    1.60
    Activations Density 1.852%

    No Known Activations