© 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. 22-GEMMASCOPE-RES-131K
    7. 14240
    Prev
    Next
    INDEX
    Explanations

    supplies, procurement, sourcing

    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_22/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
    ização
    -1.20
     گوشی
    -1.01
    ченная
    -0.94
    髖
    -0.94
     its
    -0.93
    してた
    -0.90
    昕
    -0.88
    tonsoft
    -0.88
    ssos
    -0.85
    abou
    -0.85
    POSITIVE LOGITS
     supply
    1.80
     suppliers
    1.48
     sourcing
    1.39
     purchase
    1.38
     supplier
    1.36
     procurement
    1.27
     source
    1.27
     supplies
    1.24
     sources
    1.20
     purchasing
    1.15
    Activations Density 0.078%

    No Known Activations