© 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. 34-GEMMASCOPE-RES-131K
    7. 76947
    Prev
    Next
    INDEX
    Explanations

    takes time

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

    The neuron detects words and phrases that express timing or pacing control—i.e. references to time, schedules, and moving at one’s own pace.

    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
     проще
    -0.81
    θν
    -0.80
    avits
    -0.79
     terus
    -0.77
     quick
    -0.76
    ktan
    -0.75
    unner
    -0.73
    quick
    -0.73
     Outreach
    -0.73
     vitre
    -0.73
    POSITIVE LOGITS
     slow
    2.92
     slower
    2.84
    Slow
    2.80
    slow
    2.72
     Slow
    2.61
     leisurely
    2.41
     slowed
    2.31
    ゆっくり
    2.27
     slowest
    2.20
     slowing
    2.16
    Activations Density 0.030%

    No Known Activations