© 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. 3699
    Prev
    Next
    INDEX
    Explanations

    referring to chapters

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

    chapter headings

    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
     ಹು
    0.43
    kaisi
    0.41
    寘
    0.38
    ાર્થી
    0.37
    ારીખ
    0.37
    HashCode
    0.37
    긱
    0.37
     今年
    0.36
     পত্রিকাটি
    0.36
     ڈیٹ
    0.35
    POSITIVE LOGITS
     chapter
    5.06
     Chapter
    4.75
     chapters
    4.63
    Chapter
    4.44
    chapter
    4.44
     Chapters
    4.41
     CHAPTER
    4.19
    chapters
    4.19
     capítulo
    4.13
    CHAPTER
    4.00
    Activations Density 0.234%

    No Known Activations