© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7085
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    ⬆
    0.93
     asociado
    0.86
    ื่อ
    0.83
     asoci
    0.80
     asociados
    0.79
    ื่อน
    0.77
     associés
    0.77
     associ
    0.77
    red
    0.77
    resión
    0.76
    POSITIVE LOGITS
    --){
    1.01
     depart
    0.97
    Thus
    0.96
     countDown
    0.93
     Thus
    0.91
     Depart
    0.89
    crawler
    0.89
     exceptions
    0.87
     departs
    0.86
     Nevertheless
    0.86
    Activations Density 0.029%

    No Known Activations