© 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. 28963
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations

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

    scientific abbreviations and acronyms in academic research papers.

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

    This neuron detects domain‐specific scientific acronyms and abbreviations (often including numbers or hyphens) such as MSC, HT-2, LC-HRMS, PARAFAC, MCR-ALS, etc.

    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
     However
    -1.98
     to
    -1.84
     atendido
    -1.82
    tacos
    -1.81
     its
    -1.80
     That
    -1.77
     either
    -1.74
     if
    -1.70
    océ
    -1.70
     juiz
    -1.70
    POSITIVE LOGITS
    ‘
    1.96
    our
    1.95
    his
    1.88
    s
    1.80
    m
    1.76
    your
    1.72
    two
    1.72
    i
    1.69
    ed
    1.68
    6
    1.64
    Activations Density 0.211%

    No Known Activations