© 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. 42211
    Prev
    Next
    INDEX
    Explanations

    cardiovascular, cardiopulmonary, cardiotoxicity

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

    The neuron activates for the prefix "cardio" in medical/scientific context, particularly when referring to cardiac or cardiovascular terminology.

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the prefix “cardio” (as in cardio-pulmonary, cardiovascular, cardiomyopathy, etc.) in medical terminology.

    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
     Now
    -3.52
     of
    -3.06
     Which
    -2.84
     Yeah
    -2.64
     But
    -2.56
    vantaged
    -2.48
     Given
    -2.48
     atualmente
    -2.47
     anteriormente
    -2.47
    ла
    -2.44
    POSITIVE LOGITS
    騷
    2.63
    鉭
    2.59
    ции
    2.53
    的说道
    2.47
    现在的
    2.44
    ᭝
    2.44
     essen
    2.38
    ſchen
    2.38
    焿
    2.38
     biblia
    2.36
    Activations Density 0.011%

    No Known Activations