© 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. 93877
    Prev
    Next
    INDEX
    Explanations

    month and day

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

    The neuron is detecting date units—ordinal day numbers and month names in date expressions.

    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
    Sept
    -0.94
     २०
    -0.87
    Oct
    -0.84
     Oct
    -0.81
    ${
    -0.81
    Apr
    -0.80
    مزید
    -0.79
    Ĩ
    -0.79
    Plus
    -0.78
    kov
    -0.77
    POSITIVE LOGITS
     of
    0.96
     volgende
    0.91
     years
    0.90
     religieuses
    0.89
     geluid
    0.85
    лет
    0.84
    Ӗ
    0.83
    kris
    0.83
    mustang
    0.82
    ↑↑↑
    0.82
    Activations Density 0.126%

    No Known Activations