© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13158
    Prev
    Next
    INDEX
    Explanations

    time of day

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

    The neuron is tuned to detect numeric date and time expressions (e.g. sequences of digits with slashes or colons).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CEST
    0.68
     UTC
    0.67
     GMT
    0.64
    🕕
    0.60
     svil
    0.59
     EDT
    0.59
     CTRL
    0.58
     Hours
    0.57
     inol
    0.57
     CDT
    0.56
    POSITIVE LOGITS
     morning
    0.67
    朝
    0.66
    am
    0.65
     सुबह
    0.65
    antec
    0.62
    assign
    0.57
    ulfillment
    0.55
    morning
    0.55
    ax
    0.54
     bilim
    0.54
    Activations Density 0.112%

    No Known Activations