© 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. 127606
    Prev
    Next
    INDEX
    Explanations

    government and organizational roles

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

    The neuron flags uppercase tokens naming formal organizations, governmental bodies, and official titles.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     uitgenodigd
    -1.41
    ureux
    -1.38
    antart
    -1.33
     gepubliceerd
    -1.33
    那我
    -1.32
     other
    -1.31
    Other
    -1.30
    lysm
    -1.30
    ochial
    -1.30
    RunAsync
    -1.30
    POSITIVE LOGITS
     for
    1.18
     said
    1.15
     печень
    1.13
     userDetails
    1.13
     its
    1.13
     namens
    1.11
     until
    1.05
    until
    1.04
     inoxidable
    1.04
     about
    1.03
    Activations Density 0.134%

    No Known Activations