© 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. 42670
    Prev
    Next
    INDEX
    Explanations

    gastroenterology, Magnolia, Ariana, Straits

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

    This neuron fires on the “gastroenter-” substring in medical terms (e.g. gastroenterology, gastroenteritis).

    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
     genaue
    -3.17
     wahre
    -2.72
     eigentliche
    -2.69
     gemeinsame
    -2.67
     sogenannte
    -2.61
     falsche
    -2.59
     klassische
    -2.55
    夤
    -2.55
     allgemeine
    -2.53
    jenige
    -2.52
    POSITIVE LOGITS
    s
    3.95
    </em>
    2.94
     Atención
    2.63
    岽
    2.38
     впервые
    2.38
    “
    2.33
    ଝ
    2.30
     entrée
    2.25
     Когда
    2.23
     本店
    2.19
    Activations Density 0.029%

    No Known Activations