© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102828
    Prev
    Next
    INDEX
    Explanations

    coupon codes

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

    This neuron activates on promotional or deal-related content—specifically coupon and discount offers (e.g. “coupons,” “deals,” “% off,” “free shipping,” etc.).

    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
     five
    -1.06
     four
    -1.01
     three
    -1.00
     in
    -0.98
     two
    -0.95
     for
    -0.93
     after
    -0.93
     prevent
    -0.92
     unusually
    -0.91
     if
    -0.91
    POSITIVE LOGITS
    verified
    1.30
     Coupon
    1.27
    CODES
    1.26
     coupon
    1.24
    thrift
    1.21
    codes
    1.21
    Coupon
    1.20
    coupons
    1.15
    Codes
    1.14
     coupons
    1.13
    Activations Density 0.021%

    No Known Activations