© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9162
    Prev
    Next
    INDEX
    Explanations

    pages, pagination, pp

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

    text length in words

    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_40_width_16k_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
    க்கூட
    0.42
    ikut
    0.38
     creatures
    0.37
    miller
    0.36
     downstream
    0.36
    Doe
    0.36
    倍
    0.36
     Quint
    0.35
    閾
    0.35
     trainers
    0.35
    POSITIVE LOGITS
     صفحات
    0.75
    pages
    0.73
     páginas
    0.70
     pages
    0.69
     Pages
    0.68
     PAGES
    0.68
     pagine
    0.66
     страниц
    0.65
     xvi
    0.64
    Pages
    0.63
    Activations Density 0.095%

    No Known Activations