© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15476
    Prev
    Next
    INDEX
    Explanations

    links and hyperlinks

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

    hyperlinks and URLs

    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_31_width_16k_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
    垐
    0.50
    暊
    0.49
     staffing
    0.48
    ств
    0.48
     ভর্তি
    0.48
     நிர
    0.48
    垛
    0.48
    㐬
    0.47
     ഭക്ഷണം
    0.47
    ен
    0.46
    POSITIVE LOGITS
     Links
    0.64
     hyperlinks
    0.64
     URLs
    0.59
    links
    0.59
     links
    0.57
     링크
    0.57
    link
    0.56
    Links
    0.55
     urls
    0.55
     Linking
    0.55
    Activations Density 0.064%

    No Known Activations