© 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. 4394
    Prev
    Next
    INDEX
    Explanations

    distinguishes 'v' and 'X' separators

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

    non-english script

    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
    <0xC2>
    0.49
    AAAAAAAAAAAAAAAA
    0.36
    MyToolkit
    0.35
    
    0.35
     سپورټ
    0.34
     وګټ
    0.34
    㬶
    0.34
     پوکر
    0.32
    committed
    0.32
    ButtonClick
    0.32
    POSITIVE LOGITS
     ছিলনা
    0.61
    हरु
    0.60
     أيضا
    0.58
     वक़्त
    0.56
     কোনও
    0.54
     नही
    0.54
     لئے
    0.53
     skall
    0.53
    썻
    0.53
     انها
    0.52
    Activations Density 0.237%

    No Known Activations