© 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. 85284
    Prev
    Next
    INDEX
    Explanations

    diabetes mellitus

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

    The neuron detects the medical term "diabetes mellitus" and its abbreviations like "DM" in medical and scientific texts.

    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
    𖧵
    -2.81
     ส์
    -2.72
    蟜
    -2.63
    尨
    -2.48
    羮
    -2.48
    
    -2.33
    鶲
    -2.31
    囖
    -2.31
    several
    -2.25
     overarching
    -2.25
    POSITIVE LOGITS
    $
    3.06
     There
    2.75
     Also
    2.59
     and
    2.44
     It
    2.34
    </h3>
    2.28
    (
    2.27
                
    2.23
     Then
    2.23
     But
    2.22
    Activations Density 0.013%

    No Known Activations