© 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. 127201
    Prev
    Next
    INDEX
    Explanations

    year in dates and copyright notices

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

    The main thing this neuron does is detect four‐digit year numbers.

    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
     القيام
    -1.79
    if
    -1.78
    am
    -1.74
    ۠
    -1.70
    inigung
    -1.59
    amp
    -1.48
     解説
    -1.45
     are
    -1.43
    !");
    -1.41
    fiée
    -1.41
    POSITIVE LOGITS
     alugar
    1.50
     misschien
    1.48
    魠
    1.46
    .
    1.45
     comodidad
    1.41
     kanskje
    1.41
     mobiliario
    1.38
     year
    1.36
    っていた
    1.31
     Until
    1.31
    Activations Density 0.004%

    No Known Activations