© 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. 115771
    Prev
    Next
    INDEX
    Explanations

    medical consultation and services

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

    mentions of hospitals or medical facilities.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     élégant
    -0.90
    𝑓
    -0.82
     Ife
    -0.82
    arcoma
    -0.82
    🤯
    -0.81
     Coroner
    -0.80
     Sahib
    -0.78
    massage
    -0.78
     WILLIAM
    -0.78
     STATISTICS
    -0.77
    POSITIVE LOGITS
     consultation
    1.88
     consult
    1.54
     consulting
    1.52
     consultations
    1.49
     consulted
    1.48
     consultant
    1.42
     Consultation
    1.41
    consult
    1.35
     fees
    1.32
     Consult
    1.30
    Activations Density 0.020%

    No Known Activations