© 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. 10-GEMMASCOPE-RES-131K
    7. 8616
    Prev
    Next
    INDEX
    Explanations

    when it comes time to

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

    The neuron detects phrases that signal the moment to perform an action—most notably the pattern “when it comes time to ….”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    lllllllll
    -1.38
    joyed
    -1.32
    chenen
    -1.31
    撻
    -1.31
    彼が
    -1.30
     الأخيرة
    -1.27
     vagyok
    -1.27
     empleados
    -1.26
     últimas
    -1.25
     colombiano
    -1.25
    POSITIVE LOGITS
     our
    1.57
    a
    1.48
     We
    1.42
     If
    1.41
     It
    1.39
    1.38
     sicuramente
    1.36
     eventuali
    1.35
     What
    1.34
     to
    1.34
    Activations Density 0.037%
    No Known Activations