© 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. 15703
    Prev
    Next
    INDEX
    Explanations

    testicular damage

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

    medical and anatomical terms, particularly related to testicular and other physical conditions.

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

    The neuron is detecting proper-name–style tokens (capitalized names, titles, or specialized entity labels).

    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
    这个
    -3.06
    ți
    -2.88
    ztes
    -2.86
    ቫ
    -2.80
    轳
    -2.69
    ྅
    -2.64
     だけ
    -2.58
     یک
    -2.58
    это
    -2.56
    呖
    -2.48
    POSITIVE LOGITS
     heed
    3.05
    C
    2.98
    ?”
    2.97
     ”
    2.84
    ’’
    2.80
    勿論
    2.77
     
    2.73
    ￪
    2.67
    ).”
    2.66
     the
    2.63
    Activations Density 0.069%

    No Known Activations