© 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. 14666
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and substances

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

    chemical compounds and substances in parentheses in scientific/medical texts.

    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
     it
    -2.59
    f
    -1.96
     They
    -1.96
     včetně
    -1.78
    c
    -1.73
     menengah
    -1.70
    men
    -1.69
     deines
    -1.66
    d
    -1.65
    喁
    -1.64
    POSITIVE LOGITS
     diğer
    1.66
     NACIONAL
    1.56
     또
    1.52
    acaktır
    1.50
    ambut
    1.46
    ıları
    1.44
     また
    1.43
     Gründen
    1.42
    Another
    1.42
    を考える
    1.41
    Activations Density 0.557%

    No Known Activations