© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99552
    Prev
    Next
    INDEX
    Explanations

    blood pressure and vessels

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

    The neuron detects mentions of "blood" especially in medical and scientific contexts, particularly when discussing blood pressure, blood flow, or blood components.

    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
     légende
    -0.81
     plateado
    -0.81
     Corintios
    -0.80
     couronne
    -0.78
    each
    -0.76
    と言い
    -0.75
     faculté
    -0.75
    inten
    -0.75
     Fixes
    -0.73
    噼
    -0.73
    POSITIVE LOGITS
    borne
    0.99
     vessel
    0.98
     supply
    0.98
     vessels
    0.89
    ProductService
    0.86
    >";
    0.81
    спорта
    0.80
     flow
    0.78
     */
    0.78
     loss
    0.78
    Activations Density 0.041%

    No Known Activations