© 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. 55823
    Prev
    Next
    INDEX
    Explanations

    medical causes, symptoms, and treatment

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

    sections in medical or scientific papers that list causes, symptoms, or mechanisms of conditions.

    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
     illnesses
    -0.96
     blessés
    -0.93
    ҽ
    -0.92
     tuberculosis
    -0.89
    🆙
    -0.85
     malades
    -0.85
     enfermedades
    -0.85
     problemas
    -0.85
     CANCER
    -0.85
     asthma
    -0.84
    POSITIVE LOGITS
     treatment
    2.53
     prevention
    2.47
     causes
    2.39
     symptoms
    2.33
     treatments
    1.95
     Causes
    1.84
     Symptoms
    1.82
     cause
    1.80
     signs
    1.75
    treatment
    1.70
    Activations Density 0.283%

    No Known Activations