© 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. 101803
    Prev
    Next
    INDEX
    Explanations

    blood pressure

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

    references to blood pressure in medical or scientific contexts.

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

    The neuron detects mentions of blood pressure measurements, especially numeric values or statistics associated with “blood pressure.”

    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
    s
    -2.48
    –
    -2.38
    1
    -2.06
    (
    -2.06
    …
    -2.02
    "
    -1.98
    ;
    -1.88
    .<
    -1.83
    ."
    -1.82
     —
    -1.76
    POSITIVE LOGITS
     други
    2.08
     notre
    1.96
    ”;
    1.95
     Obtén
    1.95
     bocetos
    1.91
     帅气
    1.91
    ”،
    1.88
    ſſen
    1.85
     nuestro
    1.80
    iC
    1.78
    Activations Density 0.004%

    No Known Activations