© 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. 34-GEMMASCOPE-RES-131K
    7. 60792
    Prev
    Next
    INDEX
    Explanations

    date and time stamps

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

    The neuron is triggered by numeric tokens representing clock times—i.e. hour or minute numbers that appear next to a colon in timestamps.

    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
     morning
    -1.52
    morning
    -1.08
    Morning
    -1.04
     Morning
    -0.95
     MORNING
    -0.91
     breakfast
    -0.90
     mattina
    -0.89
     mornings
    -0.84
     صبح
    -0.83
    原始内容存档于
    -0.80
    POSITIVE LOGITS
     Fortran
    0.81
    Ղ
    0.80
     skrzy
    0.78
     FORTRAN
    0.78
     mạch
    0.77
     Ine
    0.75
     Beaver
    0.74
     oğ
    0.74
    Ignored
    0.71
    champion
    0.71
    Activations Density 0.036%

    No Known Activations