© 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. 84793
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

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

    scientific compound terms and medical terminology, especially those with prefixes that describe relationships between systems.

    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
     bring
    -1.10
    حدى
    -1.04
     unrelenting
    -1.03
    والي
    -1.01
     nahezu
    -1.01
     only
    -0.96
    خلص
    -0.95
    While
    -0.93
     compelling
    -0.92
     constitutes
    -0.92
    POSITIVE LOGITS
    骉
    1.09
     kompleks
    1.08
     maig
    1.04
     spesial
    1.00
     legyen
    0.99
    lihood
    0.99
     flotte
    0.99
    нє
    0.99
     EVEN
    0.98
    jelaskan
    0.98
    Activations Density 0.244%

    No Known Activations