© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 89515
    Prev
    Next
    INDEX
    Explanations

    not all ... are equal

    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_16_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
    ﻴ
    0.64
    寺
    0.62
    یده
    0.62
    Ｉ
    0.61
    ه
    0.61
    าร
    0.60
    ‌هایی
    0.60
    ০০
    0.59
    庇
    0.59
    ढ़े
    0.59
    POSITIVE LOGITS
     is
    0.86
     not
    0.74
     מו
    0.71
    ling
    0.71
     differs
    0.68
     an
    0.67
     labels
    0.67
      
    0.67
     version
    0.66
     class
    0.66
    Activations Density 0.003%

    No Known Activations