© 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. 70994
    Prev
    Next
    INDEX
    Explanations

    periods and intervals

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

    The neuron activates on temporal expressions—words denoting time intervals, frequencies, durations, or scheduling.

    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
    毎回
    -1.02
     einmal
    -0.88
    Against
    -0.87
    crata
    -0.85
     رج
    -0.84
    komst
    -0.82
    Quels
    -0.81
    毎
    -0.81
     寝
    -0.80
     級
    -0.80
    POSITIVE LOGITS
     throughout
    2.98
     during
    2.91
     протягом
    2.63
     durante
    2.19
     since
    2.08
     протяжении
    2.06
     selama
    2.05
     until
    2.02
    throughout
    1.99
     between
    1.91
    Activations Density 0.112%

    No Known Activations