© 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. 104590
    Prev
    Next
    INDEX
    Explanations

    calendar events and dates

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

    The main thing this neuron does is detect numeric and temporal references such as dates, anniversaries, birthdays, and other event-marking tokens.

    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
     existing
    -1.05
     options
    -1.02
     experiments
    -0.97
     project
    -0.96
     опыта
    -0.96
     plans
    -0.95
     problem
    -0.93
     instructions
    -0.91
     products
    -0.90
     problems
    -0.90
    POSITIVE LOGITS
     också
    1.09
     joten
    1.09
     coincides
    1.09
     dévou
    1.08
    ynı
    1.05
    المنا
    0.97
    一応
    0.96
     also
    0.95
     hôm
    0.95
     bakteri
    0.94
    Activations Density 0.050%

    No Known Activations