© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58059
    Prev
    Next
    INDEX
    Explanations

    bovine blood vessels and cell types

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

    proper nouns, especially surnames and abbreviations related to organizations, institutions, or athletic events.

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

    This neuron strongly activates on uppercase tokens—especially acronyms and proper names (e.g. “KF,” “EKF,” “Invitational,” “McBride,” “bovine”).

    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
    </i>
    -3.44
    r
    -3.17
    u
    -3.02
    s
    -3.00
    en
    -2.88
     '
    -2.86
    la
    -2.83
          
    -2.78
    or
    -2.75
    ated
    -2.75
    POSITIVE LOGITS
    mpagne
    2.83
    糨
    2.80
    蔸
    2.67
    pecabe
    2.64
     unangemess
    2.63
    apatalk
    2.63
     mostrou
    2.59
     inimigos
    2.59
    峮
    2.55
     vodu
    2.53
    Activations Density 0.010%

    No Known Activations