© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65018
    Prev
    Next
    INDEX
    Explanations

    biological prefixes and suffixes

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

    scientific and technical terminology, particularly related to biological processes, chemical compounds, and medical terms.

    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_10/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
     who
    -2.16
    でしたが
    -1.83
     wasn
    -1.66
    seamnă
    -1.57
     was
    -1.55
    直至
    -1.49
     whom
    -1.44
     us
    -1.44
     didn
    -1.43
     Herausforderung
    -1.40
    POSITIVE LOGITS
     to
    1.88
     tersenyum
    1.57
     romantis
    1.50
     mengembangkan
    1.49
     Untuk
    1.42
     auftreten
    1.41
     Setelah
    1.38
     tertawa
    1.38
     menegaskan
    1.38
     médicaux
    1.37
    Activations Density 0.438%

    No Known Activations