© 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. 22-GEMMASCOPE-RES-131K
    7. 75230
    Prev
    Next
    INDEX
    Explanations

    hospital admissions and intensive care

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

    terms related to hospital care settings, particularly intensive care units and inpatient treatment.

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

    The neuron detects numeric quantities and statistical measurements (tokens representing numbers, counts, percentages, or decimal 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_22/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
     メニュー
    -1.11
    lijk
    -1.04
     jähr
    -0.96
     quie
    -0.95
     glaucoma
    -0.94
     chauffe
    -0.94
    J
    -0.94
     đeo
    -0.94
     pregn
    -0.94
    接続
    -0.94
    POSITIVE LOGITS
     hospital
    1.88
     facility
    1.30
     hospitals
    1.28
    Hospital
    1.24
    OSPITAL
    1.18
    ♮
    1.18
     these
    1.17
     rooms
    1.16
     ботинки
    1.16
    fohlen
    1.16
    Activations Density 0.141%

    No Known Activations