© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58308
    Prev
    Next
    INDEX
    Explanations

    epididymis

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

    scientific or technical terminology, particularly related to biology, medicine, and computer science.

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

    The neuron is selectively detecting the biomedical root “epididym–” (as in “epididymal” or “epididymis”).

    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
     are
    -1.71
     passende
    -1.63
     Sociales
    -1.56
    も見
    -1.52
     eerste
    -1.51
     themselves
    -1.51
    diferentes
    -1.50
     Agregar
    -1.50
     Selecciona
    -1.47
     such
    -1.46
    POSITIVE LOGITS
     was
    2.08
    If
    1.79
    You
    1.59
    There
    1.45
    Just
    1.31
     tricot
    1.30
    Take
    1.30
    Going
    1.30
    To
    1.24
    endente
    1.23
    Activations Density 0.138%

    No Known Activations