© 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. 66121
    Prev
    Next
    INDEX
    Explanations

    hemorrhagic

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

    This neuron detects medical terminology related to hemorrhagic conditions, specifically looking for words like "hemorrhagic," "haemorrhagic," and related bleeding disorders.

    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_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
    cedido
    -0.79
     sentier
    -0.76
    booking
    -0.76
     зае
    -0.71
    wartet
    -0.70
    　＊
    -0.69
    lihood
    -0.69
    aphthalene
    -0.68
    界的
    -0.68
    colorPrimary
    -0.68
    POSITIVE LOGITS
     transform
    0.77
    genic
    0.74
    transform
    0.73
     Кры
    0.70
     Transformers
    0.69
     tinggi
    0.68
    Kru
    0.68
    Grading
    0.67
     Crist
    0.66
    krishna
    0.66
    Activations Density 0.086%

    No Known Activations