© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11632
    Prev
    Next
    INDEX
    Explanations

    . followed by numbers or words

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

    `<!DOCTYPE html>`

    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_40_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
     윤
    0.45
     पंजाबी
    0.45
    Although
    0.44
    ᱕
    0.44
    首相
    0.43
    ↵↵↵↵↵↵↵
    0.42
    落下
    0.42
     আরম্ভ
    0.41
    윤
    0.41
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.41
    POSITIVE LOGITS
     dok
    0.47
    documentclass
    0.45
     Ekim
    0.43
     ATL
    0.42
     documentation
    0.40
     iletişim
    0.39
    हत
    0.39
     بالت
    0.39
    HashSet
    0.38
     saisi
    0.38
    Activations Density 0.001%

    No Known Activations