© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48587
    Prev
    Next
    INDEX
    Explanations

    functional outcomes and quality of life

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

    This neuron detects medical‐clinical outcome and measurement terms (e.g. words describing effects, symptoms, interventions, and their quantified results) in healthcare/scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     politica
    -0.91
     RESPONSE
    -0.91
     VOLTAGE
    -0.87
    ≠
    -0.86
     DESC
    -0.85
     wien
    -0.85
     strategie
    -0.84
     primo
    -0.84
     Epile
    -0.83
     Elektron
    -0.81
    POSITIVE LOGITS
     quality
    1.46
     functional
    1.34
     satisfaction
    1.31
     Quality
    1.23
     function
    1.21
     social
    1.19
    Quality
    1.12
     disability
    1.11
     Satisfaction
    1.09
     scores
    1.07
    Activations Density 0.334%

    No Known Activations