© 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. 58215
    Prev
    Next
    INDEX
    Explanations

    mitochondrial diseases and electrical stimulation

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

    medical and scientific terminology related to diseases, disorders, and conditions, particularly neurological and metabolic disorders.

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

    The neuron fires on technical biomedical jargon, especially terms related to mitochondrial DNA, respiratory‐chain defects, and metabolic disorders.

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.16
     uſ
    -1.15
     herrera
    -1.14
     mettent
    -1.13
    Relevant
    -1.13
    ↵↵↵↵↵↵↵↵↵↵↵
    -1.13
    KEEP
    -1.12
     goûts
    -1.12
     gomez
    -1.11
     CREATED
    -1.11
    POSITIVE LOGITS
     where
    1.65
     before
    1.61
     when
    1.56
     described
    1.50
     enables
    1.34
     just
    1.30
     utterly
    1.30
     horrific
    1.30
     requires
    1.27
     When
    1.26
    Activations Density 0.291%

    No Known Activations