© 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. 22-GEMMASCOPE-RES-131K
    7. 9326
    Prev
    Next
    INDEX
    Explanations

    time with AM/PM

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

    The neuron is detecting timestamps (times of day like “1:33 AM” or “4:03 PM”) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    nasio
    -1.02
     ibang
    -0.95
     године
    -0.94
    chafft
    -0.93
    になれば
    -0.93
     nadzieję
    -0.92
     fter
    -0.90
     میتوان
    -0.90
    になったら
    -0.89
    romes
    -0.89
    POSITIVE LOGITS
     by
    1.17
     all
    0.94
    ísticas
    0.93
    投手
    0.89
     Changed
    0.89
    🏢
    0.88
     each
    0.88
    óa
    0.88
    |_{\
    0.87
     memperbaiki
    0.87
    Activations Density 0.068%

    No Known Activations