© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47025
    Prev
    Next
    INDEX
    Explanations

    date picker wheels

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

    This neuron activates on tokens that refer to date‐picker or date/time UI components (i.e. any “date” or picker-related identifier).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    لے
    -0.81
     Satt
    -0.80
    Программа
    -0.78
     FRI
    -0.77
     puns
    -0.74
     Chicano
    -0.74
     tratto
    -0.71
     wilds
    -0.71
     объясни
    -0.71
     epa
    -0.71
    POSITIVE LOGITS
     wheel
    1.39
     Wheel
    1.34
    wheel
    1.23
    Wheel
    1.18
     wheels
    1.02
    rollers
    0.94
     cyclic
    0.93
    皰
    0.91
     Дже
    0.88
    WHEEL
    0.87
    Activations Density 0.009%

    No Known Activations