© 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. 10-GEMMASCOPE-RES-131K
    7. 11301
    Prev
    Next
    INDEX
    Explanations

    nationalities ending in 'ans' or 'ians'

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

    The neuron strongly activates on mentions of countries or national/ethnic groups (e.g. “Iranians,” “Russians,” “Europeans,” etc.).

    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
     that
    -2.53
     like
    -1.59
     as
    -1.34
    𝘜
    -1.30
    ждает
    -1.29
    三百
    -1.27
     these
    -1.27
     vierten
    -1.25
     grossen
    -1.25
     stratég
    -1.25
    POSITIVE LOGITS
     are
    1.84
    </h3>
    1.80
    zembro
    1.51
    di
    1.48
    jectable
    1.45
    hibitions
    1.44
    »,
    1.40
    
    1.39
     забезпе
    1.39
    ografi
    1.35
    Activations Density 0.029%

    No Known Activations