© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69657
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terminology

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

    scientific or technical terms related to biology, medicine, and taxonomy.

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

    The neuron consistently lights up on multi‐syllabic technical or scientific word fragments (e.g. chemical, medical, or specialized terminology).

    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
    
    -2.17
    趼
    -1.85
     dobry
    -1.85
     sierp
    -1.84
     erhi
    -1.80
     boî
    -1.78
     its
    -1.76
    probably
    -1.74
     kulinar
    -1.72
    牐
    -1.71
    POSITIVE LOGITS
     and
    2.38
     will
    1.98
     These
    1.95
    asties
    1.82
    There
    1.73
     with
    1.70
     또는
    1.68
     Università
    1.61
     Throughout
    1.59
    initializeApp
    1.56
    Activations Density 0.159%

    No Known Activations