© 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. 77901
    Prev
    Next
    INDEX
    Explanations

    angels inhabit, parents have

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

    genres, industries, humor

    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
    Not in Any Lists

    No Comments

    Negative Logits
    怀疑
    0.51
    预计
    0.48
    ಲ
    0.47
    𝓻
    0.46
     সীমাবদ্ধ
    0.46
    ुरु
    0.46
    ایی
    0.46
    attform
    0.46
    ผ
    0.46
    ﮢ
    0.46
    POSITIVE LOGITS
     соору
    0.55
     enzymes
    0.52
     Enzymes
    0.48
     enzyme
    0.48
     enz
    0.48
    enz
    0.47
     enzymatic
    0.46
     പ്രവർ
    0.46
     Enzo
    0.46
     enam
    0.45
    Activations Density 0.002%

    No Known Activations