© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 198
    Prev
    Next
    INDEX
    Explanations

    LaTeX document formatting and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lawfully
    0.33
     atualização
    0.32
    financ
    0.32
    Catherine
    0.31
     transacción
    0.31
     certeza
    0.31
     merasakan
    0.30
    َد
    0.30
    नेहा
    0.30
    كلة
    0.29
    POSITIVE LOGITS
     LaTeX
    0.45
     \
    0.44
    论文
    0.40
     {\
    0.39
     Latex
    0.38
    LaTeX
    0.38
    文献
    0.38
    {\
    0.37
     bibliography
    0.36
     ($\
    0.36
    Activations Density 0.011%

    No Known Activations