© 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. 13166
    Prev
    Next
    INDEX
    Explanations

    word followed by in

    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
    Negative Logits
    ره
    1.06
     Explained
    1.01
     Couldn
    0.99
     may
    0.96
     might
    0.96
     話
    0.96
    看来
    0.95
    զ
    0.94
    ώ
    0.94
     couldn
    0.93
    POSITIVE LOGITS
     aquilo
    1.83
     những
    1.73
     what
    1.54
     bahwa
    1.53
    នូវ
    1.53
     какие
    1.52
    what
    1.50
     aquele
    1.43
     aquela
    1.41
     какую
    1.41
    Activations Density 0.302%

    No Known Activations