© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3826
    Prev
    Next
    INDEX
    Explanations

    deals, discounts, sales

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

    The neuron detects promotional pricing language—mentions of discounts, savings, special offers, bargain deals, and their associated numbers or codes.

    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_24_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
     supl
    0.71
     dañ
    0.66
     physicochemical
    0.63
    }$')
    0.62
     Roland
    0.61
     necess
    0.61
     Suriname
    0.61
     gamut
    0.60
     annoying
    0.59
    kontrol
    0.59
    POSITIVE LOGITS
    折扣
    0.89
     Discount
    0.70
     discount
    0.69
    Discount
    0.68
     spéciale
    0.66
    ियों
    0.63
     discounts
    0.63
    ਣੀ
    0.62
    燡
    0.62
     réduction
    0.62
    Activations Density 0.007%

    No Known Activations