© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15465
    Prev
    Next
    INDEX
    Explanations

    club, visit, gin, tour, area, series

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

    scientific and technical terms

    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_31_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
     রাদ
    0.42
     '';
    0.40
    㳑
    0.39
    ঁ
    0.39
     `:`,
    0.38
    下列
    0.36
     revelar
    0.36
     seaborn
    0.36
     coasts
    0.34
     ນ
    0.34
    POSITIVE LOGITS
    і
    0.54
    от
    0.52
    또한
    0.51
     ط
    0.49
     चिन्ह
    0.48
    Пере
    0.46
    මෙ
    0.46
     ഒരു
    0.46
    ære
    0.45
    ી
    0.45
    Activations Density 0.955%

    No Known Activations