© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6793
    Prev
    Next
    INDEX
    Explanations

    asking you to tell me

    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_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Brexit
    1.10
    欧盟
    1.04
     IELTS
    0.95
    Brexit
    0.95
    ialis
    0.95
    britannien
    0.94
     republics
    0.94
     парламент
    0.92
    咲
    0.91
     EU
    0.91
    POSITIVE LOGITS
    Boy
    0.83
     thờ
    0.82
     מצ
    0.81
     Archives
    0.79
     cát
    0.78
     Zeke
    0.78
    彙
    0.78
     McBride
    0.78
     שי
    0.77
    खों
    0.76
    Activations Density 0.063%

    No Known Activations