© 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. 98289
    Prev
    Next
    INDEX
    Explanations

    buying and selling items

    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
    ationen
    -1.14
    esign
    -0.92
    𝔯
    -0.91
    Ordering
    -0.90
    appé
    -0.90
     muhimu
    -0.88
    petto
    -0.88
     Produkte
    -0.88
    ssos
    -0.88
     النظام
    -0.85
    POSITIVE LOGITS
     seller
    1.80
     auction
    1.49
     condition
    1.46
     eBay
    1.41
    igslist
    1.40
     sellers
    1.35
    Seller
    1.31
     auctions
    1.28
     bidders
    1.27
     ebay
    1.20
    Activations Density 0.034%

    No Known Activations