© 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. 53-GEMMASCOPE-2-RES-65K
    7. 17765
    Prev
    Next
    INDEX
    Explanations

    extra and related prefixes

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

    words starting with ext

    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
     additional
    0.56
    additional
    0.51
     மேலும்
    0.46
    Additional
    0.44
     Additional
    0.42
     ধাঁ
    0.38
    
    0.38
     adicional
    0.37
     lanjutan
    0.37
    俅
    0.37
    POSITIVE LOGITS
     Ext
    3.92
     extr
    3.70
    ext
    3.59
    Ext
    3.59
     экстра
    3.47
     ext
    3.33
     extrac
    3.28
    extr
    3.16
    EXT
    3.09
     extrusion
    3.03
    Activations Density 0.271%

    No Known Activations