© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 114219
    Prev
    Next
    INDEX
    Explanations

    progesterone receptor

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

    the hormone progesterone mentioned in scientific and medical contexts.

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

    The neuron detects mentions of the hormone “progesterone.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    t
    -3.14
    .
    -3.11
     estekak
    -2.89
     They
    -2.86
    ();
    -2.69
     However
    -2.41
    栳
    -2.27
     thump
    -2.25
    きました
    -2.23
     THERE
    -2.19
    POSITIVE LOGITS
    酲
    2.58
    ’
    2.48
     菇
    2.34
    ൎ
    2.33
    縠
    2.33
    !”
    2.27
    』。
    2.23
    ри
    2.23
    .’’
    2.14
    毟
    2.14
    Activations Density 0.024%

    No Known Activations