© 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. 7041
    Prev
    Next
    INDEX
    Explanations

    kidney issues, diseases, or transplants

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

    This neuron activates strongly for the word "kidney" and related terms in medical/anatomical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    臯
    -2.95
    籀
    -2.70
    倥
    -2.63
    苼
    -2.52
     donned
    -2.42
     faced
    -2.31
    नलोड
    -2.22
    湉
    -2.20
    珵
    -2.20
     tinged
    -2.19
    POSITIVE LOGITS
    狆
    2.89
    嵎
    2.83
     destinées
    2.30
     ^{\
    2.25
    
    2.22
    觔
    2.20
    at
    2.20
     and
    2.19
    ｙ
    2.11
    !");
    2.05
    Activations Density 0.018%

    No Known Activations