© 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. 39376
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations and terms

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

    The neuron activates for proper nouns and specialized terminology, particularly recognizing names of people, places, scientific terms, and acronyms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     that
    -1.86
     باتری
    -1.73
     parcs
    -1.63
    部分を
    -1.61
     wied
    -1.59
    你去
    -1.55
     inny
    -1.55
    詎
    -1.55
    eek
    -1.53
    
    -1.53
    POSITIVE LOGITS
    两个
    1.84
     имеет
    1.69
    ↵↵
    1.66
     даже
    1.65
    之前
    1.64
     ingenting
    1.64
     lisäksi
    1.50
    现在
    1.49
     mengadakan
    1.48
     вони
    1.45
    Activations Density 0.202%

    No Known Activations