© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12666
    Prev
    Next
    INDEX
    Explanations

    write once, run anywhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    an
    1.97
    a
    1.62
    en
    1.62
    u
    1.60
    s
    1.53
    า
    1.53
    ו
    1.49
    anzi
    1.47
    i
    1.36
    y
    1.34
    POSITIVE LOGITS
     的
    1.75
     手
    1.68
     出
    1.65
     使用
    1.64
     생각
    1.61
     不
    1.59
     추가
    1.56
    的小
    1.55
     是
    1.54
    ,【
    1.54
    Activations Density 0.000%

    No Known Activations