© 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. 77637
    Prev
    Next
    INDEX
    Explanations

    supply and associated actions

    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
    mpy
    -0.86
     placed
    -0.82
    Yap
    -0.72
    rogate
    -0.71
    ßten
    -0.71
    詰め
    -0.71
    Lato
    -0.71
     obs
    -0.70
     session
    -0.69
     unset
    -0.69
    POSITIVE LOGITS
     supply
    2.25
     supplied
    1.95
    supply
    1.82
    供給
    1.77
     supplying
    1.66
    supplied
    1.63
     SUPPLY
    1.59
    Supply
    1.48
     Supply
    1.41
     supplies
    1.37
    Activations Density 0.210%

    No Known Activations