© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81288
    Prev
    Next
    INDEX
    Explanations

    procurement and tenders

    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
     bokeh
    -0.87
     袋
    -0.79
    ophilic
    -0.79
    +/**
    -0.78
     FUNDS
    -0.78
     Colour
    -0.77
     balık
    -0.74
    KeyPress
    -0.73
    βά
    -0.73
    gencias
    -0.73
    POSITIVE LOGITS
     tender
    1.50
     procure
    1.36
     procurement
    1.33
     procuring
    1.25
     supplier
    1.23
     Tender
    1.20
     procured
    1.20
     Procure
    1.19
    Tender
    1.18
    tender
    1.15
    Activations Density 0.008%

    No Known Activations