© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36252
    Prev
    Next
    INDEX
    Explanations

    nationalities describing people

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

    This neuron detects mentions of a specific group or nationality (a demonym) used as the subject of a sentence.

    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
     nuestro
    -1.09
     there
    -0.96
    ép
    -0.94
     presenza
    -0.94
     if
    -0.91
     it
    -0.91
    斗争
    -0.91
     povezave
    -0.87
     queste
    -0.87
     nueva
    -0.85
    POSITIVE LOGITS
     themselves
    1.74
    themselves
    1.48
    habitants
    1.45
    Voting
    1.32
    their
    1.28
    Their
    1.25
    Assista
    1.22
    cended
    1.15
    hibited
    1.14
    hibitions
    1.13
    Activations Density 0.061%

    No Known Activations