© 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. 10198
    Prev
    Next
    INDEX
    Explanations

    fields to fill

    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
     poses
    1.67
    衅
    1.56
     타고
    1.54
     pose
    1.48
     rings
    1.43
     fame
    1.42
     hear
    1.38
     센
    1.38
     אות
    1.37
    搁
    1.35
    POSITIVE LOGITS
    २
    2.15
     formulaire
    2.06
    iele
    2.05
    restart
    2.04
    aigu
    1.99
    iburg
    1.97
    śred
    1.96
    navigate
    1.95
    Ф
    1.95
    анг
    1.94
    Activations Density 0.205%

    No Known Activations