© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113028
    Prev
    Next
    INDEX
    Explanations

    biological acronyms and abbreviations

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

    scientific notation and acronyms in parentheses, particularly in biochemical and medical research 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_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
     définiti
    -1.53
     gewähr
    -1.49
     uſe
    -1.44
    ...",
    -1.43
     daripada
    -1.43
     Diſ
    -1.41
     deinen
    -1.41
    --.
    -1.41
    You
    -1.41
    --"
    -1.39
    POSITIVE LOGITS
     大きい
    1.43
    amatan
    1.41
     هناك
    1.38
     Exteriores
    1.36
    Ṭ
    1.34
     overt
    1.34
     sings
    1.33
     such
    1.30
    bosky
    1.29
    ÓW
    1.25
    Activations Density 0.634%

    No Known Activations