© 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. 22-GEMMASCOPE-RES-131K
    7. 36264
    Prev
    Next
    INDEX
    Explanations

    work, time, and task management

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

    The neuron responds to terms describing interruptions, task-switching, and related work-load activities (e.g., “interruptions,” “task switching,” “meetings,” “appointments”).

    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
    elding
    -1.24
    seurs
    -1.14
    AndFlush
    -1.13
    Dieu
    -1.10
    ensore
    -1.09
    ittäin
    -1.09
    ellement
    -1.09
     lesen
    -1.08
    amship
    -1.05
     nobis
    -1.04
    POSITIVE LOGITS
     productivity
    1.47
     time
    1.38
    larınız
    1.31
     دیگران
    1.26
     day
    1.22
     činnosti
    1.22
     work
    1.17
     my
    1.16
     Uniwers
    1.14
     tasks
    1.13
    Activations Density 0.028%

    No Known Activations