© 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. 75887
    Prev
    Next
    INDEX
    Explanations

    online shopping and ecommerce

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    zenberg
    -0.90
    produzione
    -0.88
     immigration
    -0.84
    гти
    -0.83
    ünkü
    -0.82
    პ
    -0.81
     especialidad
    -0.81
    quran
    -0.81
    ayuno
    -0.79
     klubu
    -0.79
    POSITIVE LOGITS
     online
    2.50
     ecommerce
    2.28
     eCommerce
    2.28
     shopping
    2.22
     Amazon
    2.20
     Online
    1.91
     shoppers
    1.88
     Internet
    1.73
     Shopping
    1.71
     internet
    1.68
    Activations Density 0.060%

    No Known Activations