© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6295
    Prev
    Next
    INDEX
    Explanations

    ticket or tickets

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

    The neuron consistently lights up on numeric and quantitative tokens—digits, counts, prices, ticket numbers, statistics, and other number-related expressions.

    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_31_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
    迎え
    0.57
     ilan
    0.53
    Новости
    0.52
    歓迎
    0.52
    Furniture
    0.51
     家具
    0.51
     맞는
    0.51
    接
    0.51
     Δε
    0.50
     करिकुलम
    0.50
    POSITIVE LOGITS
     tickets
    2.63
     ticket
    2.56
     Ticket
    2.48
     Tickets
    2.47
    Tickets
    2.45
    tickets
    2.42
    Ticket
    2.36
    ticket
    2.33
    チケット
    2.17
     ticketing
    2.13
    Activations Density 0.495%

    No Known Activations