© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7829
    Prev
    Next
    INDEX
    Explanations

    history, politics, or specific topics

    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
    Not in Any Lists

    No Comments

    Negative Logits
     believed
    1.08
    \{{}\
    1.08
     disimpan
    1.07
     laterally
    1.06
     priorité
    1.04
    âncias
    1.03
    azines
    1.03
     sided
    1.03
     cassettes
    1.03
     closures
    1.02
    POSITIVE LOGITS
     го
    1.09
     Хо
    1.00
     получи
    0.97
     Edd
    0.97
     гу
    0.95
     ね
    0.94
     коре
    0.93
     Санкт
    0.91
     хо
    0.89
     Entwick
    0.89
    Activations Density 0.001%

    No Known Activations