© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14542
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron activates on date and time tokens—especially month names and numeric day/year or timestamp values.

    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
     both
    -1.20
    Zubereitung
    -1.19
    wszy
    -1.16
     tuc
    -1.16
    tauan
    -1.12
     throughout
    -1.10
     its
    -1.08
     sepenuhnya
    -1.07
     eikä
    -1.06
     行っ
    -1.06
    POSITIVE LOGITS
     heilige
    1.02
     Шаг
    1.00
     dziecko
    0.96
     obviamente
    0.95
    rédients
    0.95
     素
    0.94
     drze
    0.94
     städ
    0.93
     幼
    0.93
     yayınları
    0.93
    Activations Density 0.003%

    No Known Activations