© 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. 119384
    Prev
    Next
    INDEX
    Explanations

    medical terms / technical terms

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

    technical or specialized terminology in scientific, medical, or technical documents.

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

    The neuron consistently flags domain-specific technical terms and acronyms (e.g. disease names, protein or chemical symbols, specialized scientific abbreviations) in scientific text.

    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
     disregarding
    -2.66
     reaffirm
    -2.64
     painstaking
    -2.53
     comprehensively
    -2.52
     succinctly
    -2.47
     convincingly
    -2.45
     skillfully
    -2.42
     miraculously
    -2.42
     solidly
    -2.42
     brilliantly
    -2.42
    POSITIVE LOGITS
    It
    1.52
    散文
    1.48
    思念
    1.36
     kendaraan
    1.34
    ꯭
    1.32
    焔
    1.30
     ২০১
    1.24
    💥
    1.23
     asmen
    1.23
    Their
    1.23
    Activations Density 28.890%

    No Known Activations