© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63064
    Prev
    Next
    INDEX
    Explanations

    time formatters with minutes or seconds

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

    The neuron fires on date‐time formatting tokens and time‐unit labels (e.g. “%H”, “%M”, “days”, “hours”, “mins”, “secs”).

    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
     eight
    -0.88
    toByteArray
    -0.79
    Vec
    -0.76
    marshal
    -0.75
     four
    -0.75
     Jahre
    -0.75
     keys
    -0.74
     Shoulders
    -0.74
    バット
    -0.73
     máy
    -0.72
    POSITIVE LOGITS
     minute
    2.33
     minutes
    2.20
     Minute
    1.67
    minutes
    1.63
    minute
    1.60
    Minute
    1.47
     MINUTE
    1.45
     Minutes
    1.43
     seconds
    1.41
     minuto
    1.35
    Activations Density 0.011%

    No Known Activations