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. 29-GEMMASCOPE-2-RES-262K
    4. 690
    Prev
    Next
    INDEX
    Explanations

    раздел, категории, примеры

    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_29_width_262k_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
     variables
    1.05
     cuz
    1.03
    sthe
    1.02
     croche
    1.01
     sooo
    1.01
     QoS
    1.00
     okay
    0.99
    鏉
    0.99
    <0x07>
    0.98
     identifying
    0.98
    POSITIVE LOGITS
     Несмотря
    1.33
     Помимо
    1.29
     Для
    1.22
     Именно
    1.17
     Также
    1.15
    В
    1.14
     Благодаря
    1.13
     Однако
    1.13
     Кроме
    1.09
    На
    1.08
    Activations Density 0.057%

    No Known Activations