© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59086
    Prev
    Next
    INDEX
    Explanations

    physical examination

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

    the term "Physical examination" in medical contexts.

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

    The neuron specifically activates on the word “physical” (and its morphological variants like “physically”), marking mentions of physical attributes or measurements.

    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
    which
    -2.44
    ].
    -2.33
     encontro
    -2.22
     mehrere
    -2.14
    k
    -2.13
    >
    -2.06
    .]
    -2.06
     Now
    -2.02
    *.
    -2.00
     berço
    -1.98
    POSITIVE LOGITS
    <bos>
    2.70
    钲
    2.44
     barva
    2.33
    也會
    2.28
    谂
    2.25
     måde
    2.23
    鈈
    2.22
    ſu
    2.20
    liefert
    2.17
    安裝
    2.17
    Activations Density 0.026%

    No Known Activations