© 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. 1946
    Prev
    Next
    INDEX
    Explanations

    ecommerce platforms and solutions

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

    This neuron fires on occurrences of the substring “commerce” (e-commerce, eCommerce, Shopify/BigCommerce, etc.) whenever the text mentions commerce-related terms.

    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
    Здравствуйте
    -0.84
    ม้
    -0.83
    Calc
    -0.82
     umano
    -0.79
    我也不
    -0.76
    军团
    -0.76
     gerekti
    -0.75
     pagină
    -0.75
    あー
    -0.75
    fono
    -0.74
    POSITIVE LOGITS
     platforms
    0.94
    🛍
    0.90
     ""));
    0.88
     platform
    0.85
     sites
    0.84
    platforms
    0.83
    sites
    0.82
    getActivity
    0.81
     site
    0.80
    Platforms
    0.80
    Activations Density 0.023%

    No Known Activations