© 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. 13147
    Prev
    Next
    INDEX
    Explanations

    jobs and tasks

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

    This neuron fires on tokens naming units of work—especially “Job” or “Task” (and their plurals).

    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
    感じで
    -1.12
    ୀ
    -1.09
    grees
    -1.00
    objets
    -1.00
    albero
    -0.99
    exercice
    -0.98
     นิ้ว
    -0.97
     PUBL
    -0.96
     ندارم
    -0.96
     主题
    -0.96
    POSITIVE LOGITS
     jobs
    1.41
     ProgressDialog
    1.27
    FontAwesomeIcon
    1.26
     rescheduled
    1.23
     esegu
    1.18
     execution
    1.17
     it
    1.15
     executed
    1.13
    FirstResponder
    1.12
    rceil
    1.12
    Activations Density 0.062%

    No Known Activations