© 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. 48174
    Prev
    Next
    INDEX
    Explanations

    Eighth Circuit, eighteenth century

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

    The neuron fires on ordinal references to historical centuries (e.g., “eighteenth century,” “17th–18th centuries,” “eighteenth Amendment”).

    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
    ’
    -2.52
    憷
    -2.22
     inception
    -2.13
     sometime
    -2.06
     również
    -2.03
     hectic
    -2.00
    并未
    -2.00
     he
    -1.99
     jarring
    -1.97
     However
    -1.95
    POSITIVE LOGITS
    {
    2.69
    沇
    2.34
    Ꮙ
    2.09
    籐
    2.05
     uska
    2.03
    ！（
    2.02
     {}));
    2.02
    ？！
    2.00
    입니다
    2.00
    后感
    1.99
    Activations Density 0.012%

    No Known Activations