© 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. 9358
    Prev
    Next
    INDEX
    Explanations

    times of day and sun

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

    The neuron detects temporal expressions—especially times of day and date/time references.

    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
     night
    -2.38
     nightly
    -2.11
     tonight
    -2.11
     nights
    -2.09
     Tonight
    -2.06
    Tonight
    -1.91
    night
    -1.91
     Night
    -1.89
    Night
    -1.71
    nights
    -1.70
    POSITIVE LOGITS
     afternoon
    1.58
     lunchtime
    1.42
    Lunch
    1.42
     lunch
    1.35
     Lunch
    1.34
     sunshine
    1.29
     today
    1.27
    Afternoon
    1.23
     sunlight
    1.23
     sun
    1.20
    Activations Density 0.102%

    No Known Activations