© 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. 10-GEMMASCOPE-RES-131K
    7. 103628
    Prev
    Next
    INDEX
    Explanations

    health and technical professions

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

    occupational terms and job titles in healthcare and allied health professions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric data tokens (counts, measurements, percentages) in statistical or tabulated text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ”？
    -1.63
    ~”
    -1.49
     ?”
    -1.34
     their
    -1.26
    詬
    -1.24
     kjem
    -1.23
    :
    -1.21
     vägen
    -1.16
    '
    -1.16
     featuring
    -1.14
    POSITIVE LOGITS
    鑠
    1.27
    insegna
    1.24
    believe
    1.23
    茈
    1.23
     tecla
    1.22
     signific
    1.21
     DELHI
    1.20
     constat
    1.19
     comanda
    1.17
    fromCharCode
    1.16
    Activations Density 0.037%

    No Known Activations