© 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. 99691
    Prev
    Next
    INDEX
    Explanations

    prophylaxis and its purpose

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

    The neuron detects the medical term "prophylaxis" and related words about preventative medical treatments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on the word “prophylaxis” (and its morphological variants), i.e. mentions of preventive medical treatment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    (
    -2.53
    𖥧
    -2.41
     But
    -2.27
     There
    -2.25
    B
    -2.14
     are
    -2.11
    髣
    -1.98
    リゾート
    -1.98
     Many
    -1.95
     both
    -1.92
    POSITIVE LOGITS
     of
    2.73
    ൎ
    2.23
    🫃
    2.22
    呖
    2.16
    𖣔
    2.14
    峮
    2.08
    ༈
    2.05
    iseen
    2.03
    唻
    2.02
    䊐
    1.98
    Activations Density 0.015%

    No Known Activations