© 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. 9471
    Prev
    Next
    INDEX
    Explanations

    dates and months

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

    The neuron is tuned to spot numeric tokens—dates, times, and other 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_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
     today
    -1.70
     recently
    -1.65
     was
    -1.61
     now
    -1.45
    Today
    -1.29
     yesterday
    -1.28
     recent
    -1.27
     lately
    -1.24
    now
    -1.22
     Recently
    -1.20
    POSITIVE LOGITS
     will
    2.08
     θα
    1.27
     hopefully
    1.24
     будет
    1.23
     quadrinhos
    1.22
     serão
    1.21
     waarschijnlijk
    1.17
     majd
    1.16
    hopefully
    1.16
     estará
    1.15
    Activations Density 0.073%

    No Known Activations