© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19759
    Prev
    Next
    INDEX
    Explanations

    paediatric or old

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

    The neuron detects "pa" followed by medical or clinical terms, particularly looking for "paediatric" in medical contexts.

    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
    a
    -3.44
    ा
    -2.66
    鱨
    -2.50
    鶘
    -2.50
    ).
    -2.45
    辚
    -2.39
     edo
    -2.39
    vably
    -2.38
     yao
    -2.36
    ཋ
    -2.34
    POSITIVE LOGITS
    {
    3.31
    (
    2.69
    er
    2.48
     abhor
    2.47
    --
    2.33
    𐄁
    2.31
    先の
    2.31
     renovables
    2.30
    
    2.30
     rampant
    2.28
    Activations Density 0.003%

    No Known Activations