© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76643
    Prev
    Next
    INDEX
    Explanations

    market and places selling goods

    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
     investimento
    -0.85
    ้ม
    -0.84
     vineyards
    -0.78
    Manufacturing
    -0.78
     corp
    -0.74
    ेद
    -0.74
     escritório
    -0.73
     chestnuts
    -0.73
    properties
    -0.72
     -->
    -0.72
    POSITIVE LOGITS
     market
    3.42
     markets
    3.06
     Markets
    2.52
     Market
    2.50
    Market
    2.34
    market
    2.23
    市场
    2.14
    Markets
    2.14
    markets
    2.08
     marketplace
    2.06
    Activations Density 0.035%

    No Known Activations