© 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. 66536
    Prev
    Next
    INDEX
    Explanations

    tasks and chores

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     注
    -1.09
    Donnell
    -1.04
     (~(
    -1.03
    用于
    -1.02
     文章
    -1.01
    gy
    -1.01
    థ
    -1.01
     metodología
    -0.99
     iprot
    -0.98
    TryParse
    -0.97
    POSITIVE LOGITS
     tasks
    2.55
     task
    1.95
    tasks
    1.65
     Tasks
    1.43
    task
    1.41
     chores
    1.40
     tareas
    1.34
    もしか
    1.24
    任务
    1.23
     Task
    1.21
    Activations Density 0.031%

    No Known Activations