© 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. 53-GEMMASCOPE-2-RES-262K
    7. 15166
    Prev
    Next
    INDEX
    Explanations

    side or sides

    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_53_width_262k_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
    ปลาย
    0.42
    štu
    0.39
     端
    0.38
    REET
    0.38
    Facing
    0.38
     lont
    0.38
    ]-[
    0.38
    머
    0.38
    端的
    0.37
     end
    0.37
    POSITIVE LOGITS
     сай
    0.73
     사이
    0.70
     サイズ
    0.69
    サイト
    0.68
     साइड
    0.68
     site
    0.68
     సై
    0.67
     sides
    0.67
     സൈ
    0.67
     সাই
    0.66
    Activations Density 0.023%

    No Known Activations