© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38150
    Prev
    Next
    INDEX
    Explanations

    schedule, schedules, listing, Annex A

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

    The neuron flags numeric tokens and references to numbered items (dates, section numbers, schedules, classes, etc.).

    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
    superuser
    -0.84
     $("<
    -0.75
     Somers
    -0.75
    Slik
    -0.72
     dưỡng
    -0.72
     detuvo
    -0.72
    داری
    -0.70
    密钥
    -0.70
    unitPattern
    -0.70
    需要的
    -0.70
    POSITIVE LOGITS
     Schedule
    4.69
     schedule
    4.66
    Schedule
    4.16
     schedules
    3.97
    schedule
    3.83
     Schedules
    3.50
     SCHEDULE
    3.39
    SCHEDULE
    3.09
     scheduled
    2.80
    Schedules
    2.73
    Activations Density 0.023%

    No Known Activations