© 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. 4505
    Prev
    Next
    INDEX
    Explanations

    copyright issues involving everybody

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

    Lani McKenzie

    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
     içerisinde
    0.68
    並且
    0.64
    떄
    0.60
     গেলো
    0.57
     ​​​​
    0.57
    utilizzo
    0.54
     whatnot
    0.54
     entirety
    0.54
     चीज़
    0.54
     أيضًا
    0.54
    POSITIVE LOGITS
    Everybody
    0.48
     cominci
    0.47
     everybody
    0.46
    ῾
    0.45
     Hongkong
    0.45
     ـ
    0.44
    nobody
    0.44
     anybody
    0.44
    OK
    0.43
     somebody
    0.42
    Activations Density 0.016%

    No Known Activations