© 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. 103778
    Prev
    Next
    INDEX
    Explanations

    sent to hospital for injury

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

    references to hospitals or medical settings, especially with patients being treated.

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

    The neuron fires on mentions of hospitalization (the word “hospital” and related hospital‐care contexts).

    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
    ⚌
    -1.77
    嫒
    -1.68
     THESE
    -1.68
    扛
    -1.49
    𝘂
    -1.42
     -
    -1.36
    真的好
    -1.34
     które
    -1.33
    4
    -1.33
    梆
    -1.32
    POSITIVE LOGITS
     for
    1.40
     where
    1.40
     Gestão
    1.38
    ⌦
    1.34
    ごろ
    1.32
     vuestro
    1.30
     kerja
    1.30
     to
    1.28
     détaillée
    1.27
     investiga
    1.27
    Activations Density 0.019%

    No Known Activations