© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5549
    Prev
    Next
    INDEX
    Explanations

    places and brands

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

    call or dial

    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
    めっちゃ
    0.46
    なので
    0.45
    Awesome
    0.42
     আইডিয়া
    0.40
    整体
    0.40
    ;
    0.39
    所以在
    0.39
     colourful
    0.39
    Gorgeous
    0.39
    awesome
    0.38
    POSITIVE LOGITS
    armor
    0.40
     quorum
    0.38
     TextFormField
    0.38
     NotImplemented
    0.38
     Harwell
    0.38
    陂
    0.37
     {-
    0.37
     >,
    0.37
    onomous
    0.37
    ုံ
    0.37
    Activations Density 0.000%

    No Known Activations