© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22863
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terms

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

    scientific and technical terminology across various domains including medicine, software, and gaming.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    This neuron detects tokens that are parts of multiword proper names or technical terms (e.g. titles, personal names, drug/chemical names, diseases, or other named entities).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
     there
    -2.22
     it
    -2.02
     for
    -1.88
     two
    -1.86
     one
    -1.78
     a
    -1.76
     this
    -1.76
    :
    -1.72
     with
    -1.65
     should
    -1.65
    POSITIVE LOGITS
    Alles
    1.73
     vitale
    1.55
    ahhh
    1.50
     to
    1.45
    𓁹
    1.45
    Från
    1.40
    Efter
    1.40
     allerlei
    1.38
    sieger
    1.38
    lampen
    1.36
    Activations Density 0.369%

    No Known Activations