© 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. 69265
    Prev
    Next
    INDEX
    Explanations

    hypo + medical condition suffix

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

    the medical prefix "hypo" in terms like hypoglycemia, hypoxia, and hypothermic.

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

    The neuron activates strongly on occurrences of the “hypo” prefix in medical terms (e.g. hypoglycemia, hypoxia, hypotonia).

    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
     dritten
    -2.80
    .”
    -2.61
     แต่
    -2.44
     Their
    -2.39
     englischen
    -2.36
     ehemaligen
    -2.31
    o
    -2.27
    棪
    -2.22
     Now
    -2.17
     Förderung
    -2.17
    POSITIVE LOGITS
    ዡ
    2.89
    \
    2.69
    簷
    2.50
    voyer
    2.39
    ...»
    2.38
    羣
    2.36
    }$
    2.33
    ￪
    2.27
    s
    2.25
     ステージ
    2.23
    Activations Density 0.017%

    No Known Activations