© 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. 18960
    Prev
    Next
    INDEX
    Explanations

    nationality

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

    This neuron fires on abstract nouns ending in “-ality” (for example nationality or polarity).

    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
    orsese
    -2.86
     However
    -2.86
    iocene
    -2.67
    ！"
    -2.66
    ⣜
    -2.50
    💠
    -2.44
     With
    -2.44
    ḍ
    -2.42
     Of
    -2.38
    UCIÓN
    -2.34
    POSITIVE LOGITS
    {
    2.80
    0
    2.78
     \
    2.72
    2
    2.69
    .
    2.52
    3
    2.52
    1
    2.48
    and
    2.47
    ↵
    2.33
     of
    2.28
    Activations Density 0.004%

    No Known Activations