© 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. 34-GEMMASCOPE-RES-131K
    7. 89711
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    The neuron activates on tokens that represent numbers or numeric references (dates, scores, statistics, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     December
    -1.64
    December
    -1.53
     DECEMBER
    -1.34
     december
    -1.34
     Dec
    -1.32
    december
    -1.28
     дека
    -1.27
    Dec
    -1.25
    DECEMBER
    -1.16
     Christmas
    -1.13
    POSITIVE LOGITS
     Halloween
    1.33
    🎃
    1.20
    Halloween
    1.17
     halloween
    1.07
     Nov
    1.05
     Oct
    1.05
     Hallo
    1.02
    halloween
    0.99
     October
    0.98
    Nov
    0.93
    Activations Density 0.077%

    No Known Activations