© 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. 28955
    Prev
    Next
    INDEX
    Explanations

    Irish and other languages

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

    This neuron fires on elements of Irish/Gaelic proper names (place names and personal 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
    一些
    -1.63
    Five
    -1.62
    after
    -1.57
     five
    -1.54
    Some
    -1.53
    $
    -1.48
     Five
    -1.47
    𖥦
    -1.47
     meliputi
    -1.45
     three
    -1.40
    POSITIVE LOGITS
     realmente
    1.59
    ();
    1.59
    and
    1.58
     involucrados
    1.55
     that
    1.52
    ve
    1.48
     fantastic
    1.48
    描いて
    1.48
     réalise
    1.48
    ger
    1.47
    Activations Density 0.018%

    No Known Activations