Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110
    Prev
    Next
    INDEX
    Explanations

    daunting task or challenge

    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_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
     mö
    -0.85
    gemene
    -0.80
    =-=-
    -0.78
     图解
    -0.78
    ългария
    -0.77
     foton
    -0.77
    álogos
    -0.77
    왑
    -0.76
     Hic
    -0.74
    termilk
    -0.74
    POSITIVE LOGITS
     task
    6.19
     tasks
    4.81
    task
    4.44
    任务
    4.19
     Task
    3.77
    Task
    3.72
     assignment
    3.58
    tasks
    3.55
     mission
    3.39
     tasked
    3.39
    Activations Density 0.109%

    No Known Activations