© 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. 130964
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on mentions of clinical care levels, especially references to patients requiring nursing or monitoring care (e.g., “intermediate care patients,” “nursing care,” “intense monitoring”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    medium, moderate to large

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     spirito
    -1.00
    ば
    -0.96
     reflexiones
    -0.92
    無
    -0.91
    haviours
    -0.91
    urbo
    -0.91
     wüns
    -0.89
     حديث
    -0.89
     vecchi
    -0.85
    <0x80>
    -0.85
    POSITIVE LOGITS
     moderately
    1.79
     moderate
    1.71
     intermediate
    1.70
     level
    1.59
    intermediate
    1.55
    moderate
    1.37
     slightly
    1.37
     medium
    1.35
     légèrement
    1.31
     Intermediate
    1.30
    Activations Density 0.144%

    No Known Activations