© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7300
    Prev
    Next
    INDEX
    Explanations

    code blocks and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     quadrad
    0.96
     Voucher
    0.96
     kanggo
    0.89
     liye
    0.89
    粿
    0.88
    ларга
    0.88
    绸
    0.87
    eqa
    0.86
    Syair
    0.85
     goin
    0.85
    POSITIVE LOGITS
    -
    0.94
    ,
    0.83
    ↵
    0.72
    ders
    0.67
     giants
    0.65
    _
    0.65
    ;
    0.64
    ،
    0.63
     বন্ধুর
    0.62
     داش
    0.62
    Activations Density 0.015%

    No Known Activations