© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17350
    Prev
    Next
    INDEX
    Explanations

    links and hyperlinks

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

    links and hyperlinks

    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
    ياب
    0.45
     Überblick
    0.40
    諾
    0.39
     Nucleaire
    0.38
    doe
    0.37
    Bur
    0.37
    тик
    0.36
    一面
    0.36
    
    0.36
    bur
    0.36
    POSITIVE LOGITS
     hyperlink
    0.84
     hyperlinks
    0.83
     links
    0.81
     LINKS
    0.81
     link
    0.80
    🔗
    0.79
     Links
    0.76
    links
    0.75
     Link
    0.71
     linking
    0.71
    Activations Density 0.043%

    No Known Activations