© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 137786
    Prev
    Next
    INDEX
    Explanations

    news links to major outlets

    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
    Negative Logits
    tų
    0.59
     või
    0.59
    lių
    0.58
     Ngọc
    0.58
     to
    0.57
     다르
    0.55
     کی۔
    0.54
     Regents
    0.54
    isempty
    0.54
     ██
    0.54
    POSITIVE LOGITS
    و
    0.94
    на
    0.91
    ي
    0.89
    ه
    0.89
    ر
    0.84
    1
    0.84
    <0x0D>
    0.83
    يرا
    0.83
    ب
    0.83
    ق
    0.82
    Activations Density 0.004%

    No Known Activations