© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 17416
    Prev
    Next
    INDEX
    Explanations

    links to blogs and technical sites

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

    documentation links

    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
    BDF
    0.41
    orcid
    0.40
    @@]
    0.40
    玑
    0.40
    EndPoint
    0.39
    "),],
    0.38
    @]
    0.38
    鐫
    0.38
     প্রকল্পটি
    0.38
    gdf
    0.38
    POSITIVE LOGITS
     Blogs
    0.63
    tutorials
    0.61
     blogs
    0.61
     blog
    0.60
     Blog
    0.59
     BLOG
    0.55
     ब्लॉग
    0.55
    blogs
    0.54
     medium
    0.53
    blog
    0.52
    Activations Density 0.003%

    No Known Activations