© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90138
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    The neuron activates on tokens denoting specific dates, times, and days of the week.

    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
     September
    -1.36
     November
    -1.27
    mathrm
    -1.27
     December
    -1.21
     October
    -1.18
     January
    -1.13
     July
    -1.06
     February
    -1.05
    か月
    -1.05
    ↵
    -1.02
    POSITIVE LOGITS
     kvä
    1.09
     
    1.02
     gelukkig
    0.96
    昨日
    0.96
     gånger
    0.96
    Роман
    0.94
    materi
    0.94
     gebruikt
    0.94
     länge
    0.93
     ingår
    0.93
    Activations Density 0.038%

    No Known Activations