© 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. 11691
    Prev
    Next
    INDEX
    Explanations

    age and sepsis

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

    mentions of age in text, particularly when describing people or conditions.

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

    The neuron fires on standalone numeric measurements (especially ages, percentages, or other quantitative values).

    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
    哢
    -2.50
    
    -2.48
    ).
    -2.48
    尨
    -2.45
    ൎ
    -2.45
    迓
    -2.44
    蹀
    -2.39
    ፨
    -2.38
    涑
    -2.34
    蚰
    -2.28
    POSITIVE LOGITS
    2
    2.81
    )
    2.70
    There
    2.56
    In
    2.45
     we
    2.38
    AT
    2.31
    {
    2.23
    O
    2.22
    in
    2.22
     and
    2.14
    Activations Density 0.001%

    No Known Activations