© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15842
    Prev
    Next
    INDEX
    Explanations

    you can or like a

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

    This neuron strongly activates on tokens related to promotions (e.g. “promo,” “valide,” “get,” “you,” etc.), effectively spotting promotional-code or coupon language.

    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
    onać
    0.57
    🌓
    0.56
    🏕
    0.56
    🖼
    0.55
    autiful
    0.55
     கதா
    0.55
     confortável
    0.55
    🏞
    0.55
    😊
    0.54
     confortable
    0.54
    POSITIVE LOGITS
     coupons
    0.54
     expired
    0.49
     &
    0.48
     discount
    0.48
     listed
    0.47
     items
    0.47
     websites
    0.46
     badges
    0.46
     \&
    0.46
     information
    0.45
    Activations Density 0.000%

    No Known Activations