© 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. 108598
    Prev
    Next
    INDEX
    Explanations

    time and format

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

    This neuron activates on date‐time formatting specifiers (especially “Y”, “m”, “d” directives) within format strings.

    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
    illing
    -0.74
    Days
    -0.69
     вокруг
    -0.68
     Flick
    -0.67
     autour
    -0.67
    ву
    -0.67
    icion
    -0.66
     Ornaments
    -0.66
    unque
    -0.66
     Bunga
    -0.66
    POSITIVE LOGITS
     pukul
    2.48
     clock
    2.36
     ساعت
    2.27
     الساعة
    1.91
     às
    1.87
     Clock
    1.76
    clock
    1.73
     kl
    1.66
     hours
    1.62
    Clock
    1.59
    Activations Density 0.038%

    No Known Activations