© 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. 6898
    Prev
    Next
    INDEX
    Explanations

    then jumped

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ölt
    0.83
     zapis
    0.83
    ξει
    0.81
    新規
    0.81
    gning
    0.78
    ρ
    0.78
    gian
    0.78
    မှတ်
    0.77
    eck
    0.77
    ুটি
    0.75
    POSITIVE LOGITS
     कुत्ते
    1.17
     कुत्तों
    0.97
     Arbitration
    0.96
    arrière
    0.96
     spades
    0.94
    \{-
    0.93
    {-
    0.92
     obsług
    0.92
     messing
    0.92
    सूर
    0.90
    Activations Density 0.001%

    No Known Activations