© 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. 1786
    Prev
    Next
    INDEX
    Explanations

    today, birthdays, anniversaries

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

    The neuron strongly activates on date-related tokens—months, days, years, and “On this day…” style headings—i.e. anything marking a calendar date.

    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
     at
    -1.27
     after
    -1.09
     by
    -0.95
     when
    -0.92
     with
    -0.91
     revital
    -0.87
     amidst
    -0.86
     epitom
    -0.85
     immediately
    -0.84
    潘
    -0.83
    POSITIVE LOGITS
     today
    1.70
     Today
    1.68
     birthdays
    1.50
    Today
    1.50
     birthday
    1.41
     anniversaries
    1.40
     сегодня
    1.38
    today
    1.35
     heute
    1.31
     oggi
    1.30
    Activations Density 0.022%

    No Known Activations