© 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. 22-GEMMASCOPE-RES-131K
    7. 66676
    Prev
    Next
    INDEX
    Explanations

    scientific and medical texts

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

    scientific or technical terminology related to biological, chemical, or medical concepts.

    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_22/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
     очень
    -1.15
     Usually
    -1.10
     sogenannten
    -1.09
    関連リンク
    -1.09
     Numerous
    -1.06
     Several
    -1.05
    Usually
    -1.05
     همیشه
    -1.04
     so
    -1.04
     for
    -1.04
    POSITIVE LOGITS
     personalización
    1.17
     EconPapers
    1.10
     notificaciones
    1.06
    Plaintiff
    1.05
     búsquedas
    1.05
     actualización
    1.04
    PubMed
    1.03
    CLE
    1.03
     bezw
    1.03
     and
    1.02
    Activations Density 0.092%

    No Known Activations