© 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. 34-GEMMASCOPE-RES-131K
    7. 34962
    Prev
    Next
    INDEX
    Explanations

    pain intensity and type

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

    This neuron fires on words describing pain experiences or intensity in medical contexts.

    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
     pulmon
    -0.85
     getResource
    -0.81
    dia
    -0.81
    POSURE
    -0.80
     Ophthalmology
    -0.77
     svensk
    -0.76
     echocardio
    -0.74
    iny
    -0.74
     mutter
    -0.73
    жмите
    -0.72
    POSITIVE LOGITS
     pain
    5.53
     Pain
    4.00
    Pain
    3.98
    pain
    3.97
     PAIN
    3.22
     pains
    2.88
     painful
    2.86
     Schmerzen
    2.50
    痛
    2.42
    疼痛
    2.41
    Activations Density 0.117%

    No Known Activations