© 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. 104659
    Prev
    Next
    INDEX
    Explanations

    represented at

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

    The neuron detects mentions of nationalities or country affiliations (e.g., demonyms and country names).

    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
    foundland
    -1.49
     honom
    -1.44
     Yorkers
    -1.28
    uinal
    -1.27
     peindre
    -1.26
     alojamientos
    -1.23
     rossa
    -1.22
     genoux
    -1.21
    Additional
    -1.19
    ๗
    -1.19
    POSITIVE LOGITS
     to
    2.13
    卅
    1.30
    gilet
    1.26
     ofthe
    1.22
    MAXN
    1.20
    pedro
    1.15
     in
    1.14
    *}$
    1.13
    legion
    1.13
     who
    1.13
    Activations Density 0.053%

    No Known Activations