© 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. 70652
    Prev
    Next
    INDEX
    Explanations

    acronyms for medical conditions

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

    medical abbreviations in academic or scientific literature.

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

    The neuron strongly activates on all-caps medical acronyms (e.g., SH, BPF, RS) representing conditions or syndromes.

    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
     even
    -1.74
     даже
    -1.49
    谙
    -1.45
     
    -1.38
    Даже
    -1.33
    諳
    -1.31
     antiquated
    -1.30
     sogar
    -1.30
     despite
    -1.29
     exorbitant
    -1.27
    POSITIVE LOGITS
     a
    1.45
     maceta
    1.43
     have
    1.43
    휀
    1.42
    (!__
    1.38
    瓛
    1.35
     peças
    1.34
    ]=(
    1.34
     giac
    1.32
     usually
    1.30
    Activations Density 0.403%

    No Known Activations