© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91703
    Prev
    Next
    INDEX
    Explanations

    ticket or tickets

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

    The neuron activates on occurrences of the word “ticket” (including its plural form).

    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
     surfaces
    -0.68
    assar
    -0.68
     publiques
    -0.65
    gnal
    -0.64
     Schenk
    -0.63
     Spitzen
    -0.62
     podcasts
    -0.62
     Тро
    -0.61
    chooser
    -0.61
    phosphat
    -0.60
    POSITIVE LOGITS
     ticket
    4.78
     tickets
    4.44
    ticket
    3.59
     Ticket
    3.33
    Ticket
    3.22
    Tickets
    3.20
     Tickets
    3.09
    tickets
    3.09
     TICKET
    2.63
    TICKET
    2.53
    Activations Density 0.032%

    No Known Activations