© 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. 85410
    Prev
    Next
    INDEX
    Explanations

    morbidity and mortality

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

    The neuron detects medical and scientific terms related to "morbidity" and proper names beginning with "Ernst".

    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
    
    -2.91
    ي
    -2.77
    鏵
    -2.64
    袮
    -2.63
    鈇
    -2.59
    Ⲉ
    -2.56
    just
    -2.55
    there
    -2.45
    i
    -2.42
    甞
    -2.42
    POSITIVE LOGITS
    艫
    3.25
     unearth
    2.98
     desaparecer
    2.92
    
    2.88
     pracovní
    2.84
    力
    2.78
     sobrevivir
    2.66
     appliquer
    2.56
     describir
    2.55
    嚶
    2.55
    Activations Density 0.012%

    No Known Activations