© 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. 22-GEMMASCOPE-RES-131K
    4. 73832
    Prev
    Next
    INDEX
    Explanations

    deals and discounts

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

    The neuron activates on promotional marketing language—terms indicating special deals, discounts, coupons, and other sale-oriented offers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    porque
    -0.95
     stanovnika
    -0.93
    psc
    -0.91
    ailleurs
    -0.91
     kontaktu
    -0.90
     社会
    -0.88
     funcionalidades
    -0.88
    fourths
    -0.88
    CrossOrigin
    -0.88
    essoa
    -0.88
    POSITIVE LOGITS
     offer
    1.64
     promotions
    1.46
     offers
    1.30
    editary
    1.17
     discounts
    1.16
     offered
    1.16
     discount
    1.15
     khuyến
    1.14
     giảm
    1.13
     deal
    1.11
    Activations Density 0.030%

    No Known Activations