© 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. 78574
    Prev
    Next
    INDEX
    Explanations

    wholesale, dropshipping, suppliers

    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
     Experimental
    -0.75
    bets
    -0.73
    🏟
    -0.72
     Metern
    -0.69
     taxis
    -0.68
     heritage
    -0.68
     constitutional
    -0.68
     nu
    -0.68
     vī
    -0.68
     Jost
    -0.67
    POSITIVE LOGITS
     sourcing
    1.41
     drops
    1.38
     Sourcing
    1.30
     AliExpress
    1.29
     Drops
    1.27
     Aliexpress
    1.14
     supplier
    1.12
     suppliers
    1.10
     Shopify
    1.09
    drops
    1.03
    Activations Density 0.008%

    No Known Activations