© 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. 30944
    Prev
    Next
    INDEX
    Explanations

    health systems and book reviews

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

    healthcare facility names and medical institutions.

    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
     coincidence
    -0.80
     polí
    -0.80
    隊長
    -0.75
     soldati
    -0.73
    Lounge
    -0.73
    Ầ
    -0.70
     polygons
    -0.70
    ှ
    -0.69
     pianta
    -0.69
     cusp
    -0.68
    POSITIVE LOGITS
     system
    1.83
     System
    1.62
    system
    1.60
    System
    1.52
     SYSTEM
    1.52
     health
    1.48
     sistema
    1.46
     système
    1.46
    系统
    1.40
     hospitals
    1.34
    Activations Density 0.044%

    No Known Activations