© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25791
    Prev
    Next
    INDEX
    Explanations

    moment.js date/time manipulation

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

    The neuron detects code references to the Moment.js library (import or require calls involving “moment” and related timezone modules).

    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
    гой
    -0.87
     harvests
    -0.86
    EVA
    -0.86
     ores
    -0.84
     laman
    -0.83
     appena
    -0.82
     marts
    -0.81
     piatto
    -0.80
     Kral
    -0.79
     Mâ
    -0.79
    POSITIVE LOGITS
     Moment
    1.02
    tz
    0.96
     duration
    0.95
     Duration
    0.93
    Duration
    0.79
     moment
    0.79
     doesn
    0.78
     require
    0.76
     from
    0.75
     Asia
    0.75
    Activations Density 0.007%

    No Known Activations