© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49043
    Prev
    Next
    INDEX
    Explanations

    historical centuries

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

    This neuron detects the ordinal “th” suffix in century dates (e.g. the “th” in “19th century”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    गत
    -0.86
    ные
    -0.81
    勃
    -0.80
    PARATION
    -0.77
    ếng
    -0.77
    transaction
    -0.75
     perdita
    -0.75
     transacción
    -0.73
    sihkan
    -0.73
    Katie
    -0.73
    POSITIVE LOGITS
     century
    2.69
     Century
    1.94
    century
    1.84
    Century
    1.70
     siècle
    1.27
     siglo
    1.24
     secolo
    1.24
     CENTURY
    1.20
     centuries
    1.18
     веке
    1.13
    Activations Density 0.016%

    No Known Activations