© 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. 93156
    Prev
    Next
    INDEX
    Explanations

    medical advice and diagnosis

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

    concepts related to healthcare provider-patient relationships and medical treatment.

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

    The main thing this neuron does is identify healthcare– and medical–related terminology (e.g., patients, treatment, clinical, symptoms).

    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
    想过
    -1.13
     parfum
    -1.09
     impecable
    -1.09
     मोबाइल
    -1.05
    的目光
    -1.05
     exercice
    -1.05
     GUARANTE
    -1.04
     acqua
    -1.04
     octavo
    -1.03
     previo
    -1.00
    POSITIVE LOGITS
     treatment
    1.81
     recommend
    1.77
     diagnosis
    1.71
     recommended
    1.61
     recommendations
    1.52
     suggest
    1.51
     health
    1.46
     suggesting
    1.41
     consultation
    1.41
     advice
    1.38
    Activations Density 0.157%

    No Known Activations