© 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. 10-GEMMASCOPE-RES-131K
    7. 21084
    Prev
    Next
    INDEX
    Explanations

    medical practices and services

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects business names, particularly professional services like dental clinics, veterinary hospitals, medical practices, and other specialized establishments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     écouter
    -1.56
     ANOTHER
    -1.56
     résister
    -1.45
     admiten
    -1.44
     peculiarly
    -1.41
     itself
    -1.39
     podrán
    -1.39
     mélanger
    -1.37
     réserver
    -1.36
    糴
    -1.36
    POSITIVE LOGITS
     by
    1.95
     no
    1.66
     of
    1.59
     have
    1.52
     most
    1.38
     out
    1.37
     want
    1.37
     not
    1.37
     our
    1.34
     using
    1.34
    Activations Density 0.088%

    No Known Activations