© 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. 10-GEMMASCOPE-RES-131K
    7. 85801
    Prev
    Next
    INDEX
    Explanations

    left ventricular medical terms

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

    The neuron identifies abbreviations related to heart anatomy, particularly "LV" which stands for "left ventricle" or "left ventricular" in medical and scientific texts.

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

    The neuron activates on occurrences of the abbreviation “LV” (and related “left ventricular”) in clinical or technical contexts.

    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
    鋮
    -2.88
    箆
    -2.64
    鰱
    -2.50
    摭
    -2.48
    ”.
    -2.47
    D
    -2.41
    ”;
    -2.41
     erklär
    -2.38
    韪
    -2.38
    
    -2.36
    POSITIVE LOGITS
    ?"
    3.33
     (?)
    3.20
     "
    2.98
    !"
    2.88
    )
    2.77
    屹
    2.69
    \
    2.59
    崛
    2.56
     /
    2.55
     cette
    2.53
    Activations Density 0.007%

    No Known Activations