© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4625
    Prev
    Next
    INDEX
    Explanations

    data scraping and crawling

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

    web scraping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVelocity
    0.45
    LVector
    0.44
     commut
    0.43
     audioEngine
    0.42
    숯
    0.42
     makeSound
    0.42
    locationY
    0.41
    BinaryOperation
    0.41
     multiSelectList
    0.41
     commandBuffer
    0.41
    POSITIVE LOGITS
     scraping
    2.55
     scrape
    2.36
     scraped
    2.36
     scraper
    2.19
    scrape
    2.19
     scrapes
    2.11
    scraper
    2.05
     crawler
    1.88
    爬
    1.88
     crawling
    1.84
    Activations Density 0.050%

    No Known Activations