© 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. 104669
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

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

    the abbreviation "AED" (appearing in various contexts such as antiepileptic drugs, automated external defibrillators, and United Arab Emirates currency).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on references to automated external defibrillators—e.g. the acronym “AED” or the root “defibrill.”

    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
    ’
    -3.70
    </b>
    -3.50
    随即
    -2.75
    もお
    -2.72
     ""
    -2.67
    ↵
    -2.67
     With
    -2.52
    などと
    -2.48
    片刻
    -2.39
     encarga
    -2.39
    POSITIVE LOGITS
    衚
    3.27
    衕
    3.05
    le
    2.97
    <bos>
    2.83
    to
    2.75
    柃
    2.69
    鯪
    2.67
    騭
    2.61
    謦
    2.61
     morm
    2.61
    Activations Density 0.032%

    No Known Activations