© 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. 22-GEMMASCOPE-RES-131K
    7. 72980
    Prev
    Next
    INDEX
    Explanations

    people by nationality

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

    This neuron detects nationality or demonym adjectives (words indicating someone’s country or origin).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     przeznac
    -1.05
    d
    -1.04
     使っ
    -0.96
    önes
    -0.96
    orgio
    -0.96
     wiele
    -0.94
    msk
    -0.93
     maroon
    -0.93
     Again
    -0.93
    vv
    -0.93
    POSITIVE LOGITS
     keramik
    1.24
     klinik
    1.17
     lyd
    1.17
     retten
    1.16
     mädchen
    1.16
     parfü
    1.16
     vaksin
    1.16
     gruppe
    1.16
     ikon
    1.16
     menyen
    1.15
    Activations Density 0.041%

    No Known Activations