© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61506
    Prev
    Next
    INDEX
    Explanations

    routine medical/surgical procedures

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

    The neuron identifies the word "routine" followed by nouns representing standard medical or professional procedures.

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

    The main thing this neuron does is detect occurrences of the word “routine.”

    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
    鸸
    -1.96
     antiguas
    -1.90
     his
    -1.87
    颯
    -1.81
    ↵↵
    -1.77
    ⟣
    -1.73
     {"
    -1.70
    侑
    -1.69
    眺望
    -1.69
     ½
    -1.69
    POSITIVE LOGITS
    as
    2.16
    n
    2.14
    m
    2.09
    做的
    2.08
    fares
    2.05
     MEDIT
    1.98
    It
    1.97
    珖
    1.95
    豋
    1.89
    will
    1.84
    Activations Density 0.009%

    No Known Activations