© 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. 9254
    Prev
    Next
    INDEX
    Explanations

    physician roles and activities

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

    The neuron detects the word "physician" and related terms 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
    на
    -2.63
     affront
    -2.45
     âme
    -2.44
    ,”
    -2.41
    梃
    -2.34
     odeur
    -2.30
    の商品
    -2.28
    acterísticas
    -2.25
     kredi
    -2.25
     humeur
    -2.22
    POSITIVE LOGITS
    .
    2.84
    ↵↵
    2.84
    </td>
    2.56
     goof
    2.39
     But
    2.36
    鸸
    2.28
    ized
    2.17
     to
    2.16
     เขา
    2.08
    m
    2.06
    Activations Density 0.005%

    No Known Activations