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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12445
    Prev
    Next
    INDEX
    Explanations

    HTML tag `dialog`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_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
    日本語
    0.28
     wich
    0.27
    </
    0.26
     extensible
    0.26
    ylar
    0.26
     countable
    0.25
     Belarus
    0.25
     enumerated
    0.25
     beneficial
    0.25
     leukocyte
    0.25
    POSITIVE LOGITS
    വർ
    0.30
    Missouri
    0.30
     دليل
    0.29
     ຂ
    0.28
    عنی
    0.28
     ਆਪਣੇ
    0.28
    ಭವ
    0.28
     задание
    0.27
    ΟΥ
    0.27
     quarts
    0.27
    Activations Density 0.016%

    No Known Activations