© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2192
    Prev
    Next
    INDEX
    Explanations

    stage, time, source, horizon

    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
    juje
    0.90
    ק
    0.89
    валася
    0.86
     тоді
    0.86
     Economic
    0.86
    പക്ഷ
    0.85
     Jerzy
    0.85
    ခဲ့
    0.85
     chronology
    0.84
     bacilli
    0.84
    POSITIVE LOGITS
    每
    1.16
     everytime
    1.16
    每一
    1.15
     κάθε
    1.11
     mỗi
    1.11
     каждой
    1.10
     each
    1.07
     ஒவ்வொரு
    1.06
     iedere
    1.05
     EACH
    1.04
    Activations Density 0.484%

    No Known Activations