© 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. 81209
    Prev
    Next
    INDEX
    Explanations

    reproductive health areas

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

    academic or scientific text in research papers or reports.

    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
    aneity
    -1.32
    zied
    -1.01
    ׇ
    -1.00
     kampus
    -0.99
    nological
    -0.99
    alogical
    -0.99
     bakal
    -0.97
     macOS
    -0.95
     tanam
    -0.94
    茹で
    -0.93
    POSITIVE LOGITS
     WHO
    1.43
     country
    1.23
     health
    1.23
    WHO
    1.16
     epidemio
    1.11
    ֶּ
    1.06
     Lancet
    1.05
     maternal
    1.00
     surveillance
    0.99
    卫生
    0.99
    Activations Density 0.178%

    No Known Activations