© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102367
    Prev
    Next
    INDEX
    Explanations

    blood flow and circulation

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

    references to blood flow in medical and physiological contexts.

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

    The neuron activates on phrases describing blood flow or related hemodynamic measurements.

    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
     nôtre
    -1.45
    と同じ
    -1.43
    ゛
    -1.41
    aaral
    -1.41
    ヨーロ
    -1.38
     sélections
    -1.38
     クッキー
    -1.37
    </i>
    -1.36
     gắng
    -1.35
    urbs
    -1.34
    POSITIVE LOGITS
     américa
    1.53
    enablog
    1.48
     including
    1.41
     />";
    1.38
     is
    1.38
     JOHN
    1.30
    了一会儿
    1.29
    y
    1.23
     popoli
    1.23
    tieth
    1.23
    Activations Density 0.084%

    No Known Activations