© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113628
    Prev
    Next
    INDEX
    Explanations

    Coronary Artery Bypass Grafting

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

    acronyms and technical terms, particularly in medical and scientific contexts.

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

    The neuron fires on domain‐specific jargon tokens—uncommon technical terms and abbreviations (e.g. scientific names or medical acronyms).

    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
    ↵
    -3.33
    a
    -3.02
    .
    -2.84
    
    -2.84
    an
    -2.83
    I
    -2.58
    1
    -2.50
    ஂ
    -2.47
    -
    -2.47
    one
    -2.44
    POSITIVE LOGITS
    
    2.73
    
    2.64
     But
    2.59
    舁
    2.55
     paroisse
    2.42
    杁
    2.36
    湉
    2.34
    嵙
    2.30
    ophores
    2.27
     jangan
    2.25
    Activations Density 0.022%

    No Known Activations