© 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. 87283
    Prev
    Next
    INDEX
    Explanations

    viruses

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

    mentions of viruses, particularly detecting "virus" and related terms in scientific or medical contexts.

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

    The neuron activates on mentions of viruses or viral entities.

    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
    [
    -3.25
    不是很
    -2.69
    *
    -2.63
    .”
    -2.61
    ?
    -2.48
     sorta
    -2.41
    过后
    -2.36
    但却
    -2.27
    都是在
    -2.23
    .!
    -2.17
    POSITIVE LOGITS
    ⃚
    2.39
     powinny
    2.28
    یمت
    2.17
    ﻂ
    2.17
     ถ้า
    2.14
    锷
    2.14
    ⑧
    2.08
    產生
    2.03
     เปิด
    2.03
    ೣ
    2.02
    Activations Density 0.020%

    No Known Activations