© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57761
    Prev
    Next
    INDEX
    Explanations

    questions and e-commerce context

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

    The neuron fires on tokens in an e-commerce “Shipping & Returns” (and related policy) section—especially on headings like “Shipping,” “Returns,” “Cancellations,” and the surrounding policy text.

    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
     even
    -1.22
     v
    -1.13
     their
    -1.09
    :
    -1.05
     духовке
    -1.03
     now
    -0.95
     p
    -0.92
     told
    -0.92
     asked
    -0.91
    ;
    -0.91
    POSITIVE LOGITS
     Shopify
    1.64
    Shopify
    1.37
     objedná
    1.16
    Shipping
    1.13
     customer
    1.12
    Customer
    1.11
     subtotal
    1.10
    MERCE
    1.07
    Returns
    1.05
    shipping
    1.05
    Activations Density 0.061%

    No Known Activations