© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2587
    Prev
    Next
    INDEX
    Explanations

    extend or expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    呜
    0.64
    æss
    0.64
    فيف
    0.60
    仕
    0.58
    嵓
    0.57
    лимпи
    0.57
    ὧ
    0.57
     শ্রদ্ধা
    0.56
    初心
    0.56
    诰
    0.56
    POSITIVE LOGITS
     extension
    5.22
     extend
    4.99
     extensions
    4.96
     Extension
    4.92
    Extension
    4.75
    extension
    4.73
     Extend
    4.66
     extended
    4.65
    Extend
    4.63
    extend
    4.62
    Activations Density 1.135%

    No Known Activations