© 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. 42593
    Prev
    Next
    INDEX
    Explanations

    identifiers for diseases

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

    The neuron detects the word "biomarkers" particularly in medical and scientific research contexts.

    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
     или
    -2.56
     While
    -2.52
     voeten
    -2.22
    倏
    -2.19
     It
    -2.19
     multitude
    -2.17
     mengisi
    -2.17
     Bagaimana
    -2.14
     scandalous
    -2.11
    "
    -2.11
    POSITIVE LOGITS
    苼
    2.45
    箆
    2.38
     เขา
    2.38
    鐽
    2.31
    .
    2.31
     哪些
    2.30
     插图
    2.23
    
    2.23
    n
    2.22
    b
    2.22
    Activations Density 0.012%

    No Known Activations