© 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. 10-GEMMASCOPE-RES-131K
    7. 73967
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron specializes in detecting numeric tokens that form parts of dates (e.g. day, month, or year values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     in
    -1.73
     for
    -1.72
    2
    -1.61
     with
    -1.48
     немає
    -1.46
    どうやって
    -1.44
     ждет
    -1.43
     as
    -1.43
    up
    -1.42
    其实是
    -1.41
    POSITIVE LOGITS
    
    1.63
     it
    1.55
    一愣
    1.52
    嗵
    1.50
     "";
    1.50
    âni
    1.47
     skóry
    1.46
    錾
    1.41
    珰
    1.41
     каждый
    1.40
    Activations Density 0.125%

    No Known Activations