© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208016
    Prev
    Next
    INDEX
    Explanations

    ordering for following phrases

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

    side opposite

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    م
    0.50
    ใหญ่
    0.48
     مكت
    0.47
    ⭐⭐
    0.46
     Upstairs
    0.46
    //////////////
    0.46
     ইঙ্গিত
    0.46
    Tight
    0.44
    锜
    0.44
    Lack
    0.44
    POSITIVE LOGITS
    rian
    0.53
    rians
    0.47
    рована
    0.47
    boat
    0.46
    roids
    0.46
    adece
    0.46
    ütfen
    0.45
    gomery
    0.44
    imantan
    0.44
    jda
    0.44
    Activations Density 0.002%

    No Known Activations