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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54540
    Prev
    Next
    INDEX
    Explanations

    medical terminology

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

    This neuron detects medical and technical terminology, particularly in scientific contexts like anatomy, biology, and engineering.

    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_22/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
     products
    -1.04
    vák
    -1.02
     funkcji
    -1.01
    ﮨ
    -1.01
     objects
    -1.00
     useful
    -0.97
    出了
    -0.93
     of
    -0.93
    ్యా
    -0.93
     gó
    -0.91
    POSITIVE LOGITS
     eerst
    1.07
     gänzlich
    1.01
    États
    0.94
    误会
    0.93
    同一个
    0.90
    不愿意
    0.90
    纷
    0.88
     anhand
    0.87
     entraîner
    0.87
     hinsichtlich
    0.86
    Activations Density 0.110%

    No Known Activations