© 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. 77961
    Prev
    Next
    INDEX
    Explanations

    procurement and purchasing

    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
     Customers
    -1.11
    Customers
    -1.05
    sales
    -1.03
    sells
    -1.03
    customers
    -1.02
     SALES
    -1.02
    SALES
    -1.01
    Sales
    -0.98
    sold
    -0.96
    CUSTOMER
    -0.96
    POSITIVE LOGITS
     procurement
    2.80
     purchasing
    2.63
     Procurement
    2.28
     purchase
    2.20
     Purchasing
    2.16
     purchases
    2.05
    Procurement
    2.02
    Purchasing
    1.94
    采购
    1.91
     procure
    1.90
    Activations Density 0.022%

    No Known Activations