© 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. 22-GEMMASCOPE-RES-131K
    7. 26949
    Prev
    Next
    INDEX
    Explanations

    duration and time values

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

    The main thing this neuron does is find numeric literals (including integers and decimals) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ־ה
    -1.05
     in
    -1.05
    if
    -0.92
     выгля
    -0.92
     recommended
    -0.92
    monium
    -0.91
    ufel
    -0.91
    号
    -0.91
    version
    -0.91
     number
    -0.90
    POSITIVE LOGITS
     duration
    1.32
     시간
    1.29
     time
    1.21
    esgue
    1.15
     estimado
    1.09
     milliseconds
    1.09
    Duration
    1.08
    ٦
    1.08
     seconds
    1.05
     لمدة
    1.05
    Activations Density 0.006%

    No Known Activations