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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3617
    Prev
    Next
    INDEX
    Explanations

    automating tasks, chores, and the mundane

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    दर्श
    0.79
    Attenuation
    0.75
     '\\;'
    0.71
     отобра
    0.69
     metastability
    0.69
     exponentes
    0.68
    HashMap
    0.68
    Theory
    0.68
     cinética
    0.67
    權
    0.66
    POSITIVE LOGITS
     tasks
    2.55
     chores
    2.34
     Tasks
    2.23
     tarefas
    2.20
     tareas
    2.20
    tasks
    2.05
     tâches
    2.05
     housework
    2.05
     task
    1.86
    Tasks
    1.85
    Activations Density 0.587%

    No Known Activations