© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37789
    Prev
    Next
    INDEX
    Explanations

    shipping costs and delivery

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

    The neuron fires on tokens that specify numeric pricing details and cost breakdown (e.g. dollar amounts, “plus,” “tax,” “shipping”).

    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
     party
    -0.78
    焉
    -0.75
     purchases
    -0.73
     Krankheit
    -0.72
     maquiagem
    -0.72
     pobreza
    -0.70
     cabezas
    -0.69
     riqueza
    -0.69
     possono
    -0.69
    food
    -0.69
    POSITIVE LOGITS
     shipping
    2.89
     postage
    2.63
     Shipping
    2.05
    shipping
    2.05
    Shipping
    2.03
    送料
    1.91
     Postage
    1.72
    SHIPPING
    1.63
     SHIPPING
    1.47
    运
    1.45
    Activations Density 0.024%

    No Known Activations