© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99930
    Prev
    Next
    INDEX
    Explanations

    coupon codes

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

    The neuron activates on mentions of coupons or promotional codes (e.g., the words “coupon,” “code,” or “promo code”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ☑️
    -1.64
     */
    -1.58
    ？！
    -1.55
    玩具
    -1.54
    ？（
    -1.53
     даже
    -1.51
    ку
    -1.47
    。。。。
    -1.44
    流星
    -1.43
    描写
    -1.41
    POSITIVE LOGITS
     우리
    1.77
     our
    1.69
    <i>
    1.64
    给我们
    1.53
    我们要
    1.53
     اصفه
    1.50
     عف
    1.48
     köln
    1.46
     następnie
    1.45
    我们的
    1.40
    Activations Density 0.009%

    No Known Activations