© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 225
    Prev
    Next
    INDEX
    Explanations

    function calls and delimiters

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

    items followed by commas

    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
    positroid
    0.36
    ्रेंस
    0.35
    橑
    0.35
    砵
    0.35
    斯的
    0.34
     adhesives
    0.33
     মুক্তিফৌজ
    0.33
    睺
    0.33
    手的
    0.32
     তাহাই
    0.32
    POSITIVE LOGITS
    ,)
    0.72
    ,),
    0.70
    ,
    0.69
    )
    0.66
    (),
    0.66
    ),
    0.66
    ,'
    0.65
     ,
    0.64
    ,{
    0.64
    ,@
    0.64
    Activations Density 0.016%

    No Known Activations