© 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. 90225
    Prev
    Next
    INDEX
    Explanations

    ticket sales, prices, and offices

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

    The main thing this neuron does is detect mentions of tickets and ticket-sales or ticket-purchase information.

    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
     of
    -1.12
    _
    -0.98
    f
    -0.94
     \
    -0.94
    Creators
    -0.93
    k
    -0.93
    警惕
    -0.92
    b
    -0.90
     .
    -0.88
    ip
    -0.88
    POSITIVE LOGITS
    🎫
    1.34
    🎟
    1.25
     sales
    1.13
     sold
    1.13
     sprzedaży
    1.09
     bought
    1.07
     holders
    1.06
     purchased
    1.06
     VALVE
    1.05
     purchaser
    1.01
    Activations Density 0.010%

    No Known Activations