© 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. 71705
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terms

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

    scientific text with citations and statistics in academic papers.

    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
     atelier
    -1.20
     TOY
    -1.10
     baf
    -1.09
     afp
    -1.06
     staten
    -1.05
     Ayur
    -1.04
     sobri
    -1.03
     Fellowships
    -1.03
     territo
    -1.02
     pulmon
    -1.02
    POSITIVE LOGITS
    ncbi
    1.46
     studies
    1.29
     Tieren
    1.23
     Journal
    1.23
     study
    1.20
    Studies
    1.17
    doi
    1.14
     dekol
    1.14
     Wisconsin
    1.12
     Proceedings
    1.12
    Activations Density 0.116%

    No Known Activations