© 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. 10-GEMMASCOPE-RES-131K
    7. 118940
    Prev
    Next
    INDEX
    Explanations

    drug names

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

    pharmaceutical drug names.

    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
     this
    -1.73
     what
    -1.52
     which
    -1.41
     through
    -1.39
    ',
    -1.38
    ۞
    -1.35
     from
    -1.35
    Pubs
    -1.29
     would
    -1.27
    '
    -1.25
    POSITIVE LOGITS
     refroid
    1.66
     также
    1.52
     también
    1.51
     calorías
    1.49
     artículos
    1.49
    三个
    1.49
    所有的
    1.47
    ꉂ
    1.47
     alkoholu
    1.46
    ーーー
    1.45
    Activations Density 0.199%

    No Known Activations