© 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. 34-GEMMASCOPE-RES-131K
    7. 45441
    Prev
    Next
    INDEX
    Explanations

    hemorrhagic fevers and encephalitis

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

    This neuron detects terms related to viral diseases, particularly hemorrhagic fevers and virus strains.

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

    The neuron activates on terms naming hemorrhagic fever viruses and related disease-name phrases (e.g. “hemorrhagic fever with renal syndrome,” “Omsk hemorrhagic fever,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Poz
    -0.73
     perla
    -0.69
     tiap
    -0.68
     brengen
    -0.67
     each
    -0.65
     holomorphic
    -0.65
     niezbęd
    -0.65
     Contributions
    -0.65
    Чи
    -0.64
     berjudul
    -0.63
    POSITIVE LOGITS
     Marburg
    0.91
     bleeding
    0.90
     filo
    0.88
     hemorr
    0.80
    PTT
    0.79
     ARN
    0.77
     gron
    0.77
    $(".
    0.77
    ARB
    0.77
    ぇ
    0.76
    Activations Density 0.028%

    No Known Activations