© 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. 75556
    Prev
    Next
    INDEX
    Explanations

    intensive care unit

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

    The neuron detects references to intensive care units (ICU), with particularly strong activation for the phrases "intensive care" and "care units."

    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
    tamaris
    -1.83
    我一直
    -1.81
    噥
    -1.78
    釙
    -1.75
     geldig
    -1.72
    数を
    -1.72
     pakan
    -1.72
    '])->
    -1.70
    vidéo
    -1.66
     美しい
    -1.65
    POSITIVE LOGITS
    .
    1.71
    s
    1.58
    www
    1.51
    we
    1.50
    見
    1.45
     $\
    1.44
     is
    1.38
    ètement
    1.38
    itigen
    1.34
     course
    1.34
    Activations Density 0.027%

    No Known Activations