© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99177
    Prev
    Next
    INDEX
    Explanations

    sellers and merchants

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

    The neuron is triggered by e-commerce context terms, especially words around sellers, marketplaces, and orders.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     client
    -0.90
     клиент
    -0.88
    购买
    -0.81
     заказ
    -0.81
     kule
    -0.79
     compra
    -0.78
     客户
    -0.77
    purchase
    -0.77
     Client
    -0.77
    下单
    -0.77
    POSITIVE LOGITS
     seller
    1.78
     sellers
    1.75
     Seller
    1.43
     store
    1.34
     selling
    1.30
     Sellers
    1.30
    seller
    1.27
     merchants
    1.27
     shop
    1.24
     продав
    1.24
    Activations Density 0.025%

    No Known Activations