© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87144
    Prev
    Next
    INDEX
    Explanations

    order fulfillment

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

    The neuron fires on the characteristic language and tokens of an e-commerce order/shipment notification (e.g. “shipped your items today,” “track your order,” Amazon URLs, order-completion phrases).

    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
     blog
    -0.81
     prototypes
    -0.77
    crust
    -0.75
     prototype
    -0.72
     deposition
    -0.71
    lipse
    -0.71
     Email
    -0.71
    top
    -0.69
     konuş
    -0.69
    SourceChecksum
    -0.68
    POSITIVE LOGITS
     fulfilled
    1.76
    fulfilled
    1.63
     Ful
    1.59
     Amazon
    1.57
     Prime
    1.54
    Ful
    1.44
    Amazon
    1.41
    Prime
    1.41
     Fulfillment
    1.37
     fulfilment
    1.34
    Activations Density 0.024%

    No Known Activations