© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10368
    Prev
    Next
    INDEX
    Explanations

    lists correspond

    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_7_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
     美
    1.91
     금
    1.82
     piy
    1.74
     金
    1.68
    უფ
    1.68
     گر
    1.62
     保
    1.61
     인터넷
    1.57
     久
    1.57
    氯
    1.55
    POSITIVE LOGITS
     experimental
    1.52
     দিয়েছেন
    1.44
    nales
    1.44
    টাও
    1.41
     submanifold
    1.40
    เตรียม
    1.37
    лил
    1.35
     acte
    1.35
    a
    1.31
     subsurface
    1.30
    Activations Density 0.019%

    No Known Activations