© 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. 39925
    Prev
    Next
    INDEX
    Explanations

    medical/scientific terms ending in 'tomy' or 'MAC'

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

    technical and scientific terminology, particularly related to medical procedures, computer systems, and acronyms.

    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
    其妙
    -3.64
    ي
    -3.53
    ি
    -2.97
    ी
    -2.92
    我没
    -2.89
    好在
    -2.84
    ۷
    -2.75
     Vorsitzende
    -2.72
    我也是
    -2.72
    acterísticas
    -2.72
    POSITIVE LOGITS
    o
    3.17
    d
    3.17
    e
    3.14
    灩
    3.05
    A
    3.03
    h
    2.94
    的
    2.70
    ならない
    2.67
    _
    2.67
    man
    2.61
    Activations Density 0.037%

    No Known Activations