© 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. 22-GEMMASCOPE-RES-131K
    7. 73344
    Prev
    Next
    INDEX
    Explanations

    programming time

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

    The neuron is tuned to pick up references to the “time” module or package (e.g. import or use of “time”).

    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
     جایی
    -1.02
     bogs
    -0.98
     ranting
    -0.96
    DayOfWeek
    -0.96
     Scritto
    -0.94
    HEARING
    -0.93
     koń
    -0.92
     Externe
    -0.91
     Erster
    -0.90
    istiques
    -0.90
    POSITIVE LOGITS
     time
    1.05
    ⌛
    1.02
     waiting
    1.01
     wait
    0.99
     لمدة
    0.99
     say
    0.96
    rophe
    0.94
     vänt
    0.94
    रोध
    0.93
     and
    0.92
    Activations Density 0.010%

    No Known Activations