© 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. 54363
    Prev
    Next
    INDEX
    Explanations

    next or last days of the week

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

    The neuron fires on words that signal temporal ordering or reference time (e.g. “next,” “last,” “following,” “second,” “first”).

    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
     Nights
    -0.86
    譎
    -0.83
     garder
    -0.80
    those
    -0.79
     DAYS
    -0.77
     всички
    -0.76
     pará
    -0.75
     prehistoric
    -0.75
    ||||
    -0.74
    日間
    -0.74
    POSITIVE LOGITS
     week
    2.64
     weekend
    2.23
     weeks
    1.80
     weekends
    1.62
    week
    1.59
     month
    1.57
     semana
    1.50
     Wednesday
    1.41
    weekend
    1.35
     Tuesday
    1.32
    Activations Density 0.041%

    No Known Activations