© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7998
    Prev
    Next
    INDEX
    Explanations

    PayPal

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

    The neuron activates on terms and phrases related to auctions and selling on eBay.

    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_31_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
     callBack
    0.60
    CallBack
    0.59
    🍗
    0.59
    👷
    0.59
     коктей
    0.58
    orsese
    0.57
    🥛
    0.57
    捗
    0.57
    💧
    0.56
    🏗
    0.56
    POSITIVE LOGITS
     eBay
    2.02
     ebay
    1.98
    eBay
    1.94
     Ebay
    1.88
    ebay
    1.66
     auctions
    1.60
     Auctions
    1.47
     auction
    1.44
    Auction
    1.44
     seller
    1.34
    Activations Density 0.357%

    No Known Activations