© 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. 10-GEMMASCOPE-RES-131K
    7. 90697
    Prev
    Next
    INDEX
    Explanations

    on dates and times

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

    The neuron strongly activates on the word “on” when it appears in email header lines immediately before dates or timestamps.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -1.73
     kangoo
    -1.58
     કર
    -1.56
     TECHNI
    -1.48
     sains
    -1.47
     chicco
    -1.45
     teater
    -1.45
     lampa
    -1.44
     EXERC
    -1.43
     maky
    -1.41
    POSITIVE LOGITS
     why
    1.79
     disfrutando
    1.59
     inicialmente
    1.56
     escritores
    1.50
     esperan
    1.47
     ultimately
    1.45
     által
    1.39
     suficientemente
    1.37
     viviendo
    1.37
    tetés
    1.33
    Activations Density 0.014%

    No Known Activations