© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60453
    Prev
    Next
    INDEX
    Explanations

    elective medical procedures

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

    The neuron detects the word "elective" when referring to scheduled or planned surgical procedures.

    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
    1
    -3.39
    2
    -3.22
     
    -2.61
    </h1>
    -2.39
    <i>
    -2.30
    <h2>
    -2.30
      
    -2.19
     He
    -2.19
    3
    -2.13
    0
    -2.09
    POSITIVE LOGITS
    ！”
    2.86
    䛗
    2.75
     сист
    2.63
     initWithFrame
    2.59
    ൎ
    2.48
    鸶
    2.47
    طفال
    2.45
    zboi
    2.42
    檍
    2.41
    泺
    2.36
    Activations Density 0.003%

    No Known Activations