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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 889
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_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
     zlep
    0.95
     व्याप्त
    0.94
     सहस्त्र
    0.83
     humiliated
    0.83
    tugraz
    0.83
    ormal
    0.82
     tràn
    0.81
    |^{
    0.80
     нару
    0.80
    恢復
    0.79
    POSITIVE LOGITS
     choice
    4.62
     choosing
    4.49
    choice
    4.24
     choices
    4.23
    选择
    4.21
     choix
    4.18
     Choice
    4.12
     escolha
    4.07
     chọn
    4.07
    選擇
    4.05
    Activations Density 4.394%

    No Known Activations