© 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. 69392
    Prev
    Next
    INDEX
    Explanations

    clin prefix followed by medical descriptions

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

    The neuron detects the word "Clinically" at the beginning of a sentence in medical or scientific texts.

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

    The neuron specifically fires on mentions of clinical context markers (e.g. “Clinically,” “clinical”) in the 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
    卺
    -2.94
     It
    -2.42
    </h3>
    -2.30
     Não
    -2.13
     semelh
    -2.02
    驺
    -1.95
     Regarding
    -1.95
     lauded
    -1.84
    旆
    -1.83
    皛
    -1.82
    POSITIVE LOGITS
    _
    2.08
     grupper
    2.00
    Those
    1.99
    {
    1.90
    ”(
    1.88
    With
    1.88
    Without
    1.87
    ﹔
    1.84
    Even
    1.84
    (
    1.84
    Activations Density 0.052%

    No Known Activations