© 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. 34-GEMMASCOPE-RES-131K
    7. 3633
    Prev
    Next
    INDEX
    Explanations

    countries and nationalities

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

    The neuron strongly activates on country names and nationality adjectives (e.g. “Swedish,” “British,” “Norway”), i.e. references to national or geographic identities.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    India
    -1.15
     india
    -1.15
     indian
    -1.09
    india
    -1.02
     India
    -0.98
     Indian
    -0.97
     wording
    -0.97
    印度
    -0.96
     Indien
    -0.94
     preventative
    -0.93
    POSITIVE LOGITS
     upto
    1.38
    upto
    1.27
     equipments
    1.05
     atleast
    1.02
     alphabets
    1.02
     till
    1.01
     artistes
    1.01
     étranger
    0.98
     apprehensions
    0.94
     thrice
    0.92
    Activations Density 0.045%

    No Known Activations