© 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. 34-GEMMASCOPE-RES-131K
    7. 116456
    Prev
    Next
    INDEX
    Explanations

    August dates

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

    The neuron fires on date and time tokens (e.g. month names, day and year numbers), effectively spotting date or timestamp mentions.

    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
     február
    -1.04
     february
    -1.00
     vinter
    -0.88
     april
    -0.87
     január
    -0.85
     Eurovision
    -0.83
     january
    -0.82
    February
    -0.82
    正月
    -0.81
    パンマン
    -0.79
    POSITIVE LOGITS
     August
    2.64
    August
    2.42
     Aug
    2.30
    Aug
    1.96
     agosto
    1.91
     авгу
    1.89
     AUGUST
    1.86
    AUGUST
    1.84
    august
    1.70
     août
    1.67
    Activations Density 0.045%

    No Known Activations