© 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. 10089
    Prev
    Next
    INDEX
    Explanations

    clinico-pathological

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

    The neuron detects medical and anatomical compound terms with hyphens, particularly those with suffixes like "-ico-", "-to-", and other anatomical prefixes.

    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
    
    -1.65
    )।
    -1.62
    Ambos
    -1.60
    niająca
    -1.55
    )
    
    -1.54
    :
    
    -1.52
    Osob
    -1.52
    ">
    
    -1.50
     for
    -1.49
     любого
    -1.48
    POSITIVE LOGITS
    骉
    1.73
     滅
    1.64
     nogle
    1.62
    MAGAZINE
    1.59
     gebruiken
    1.59
     苹果
    1.57
     直播
    1.52
     汽车
    1.52
     安卓
    1.50
     написал
    1.48
    Activations Density 0.032%

    No Known Activations