© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13810
    Prev
    Next
    INDEX
    Explanations

    Argentina won the World Cup

    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_7_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
    ඪ
    2.31
    ඥ
    2.22
     නිෂ්
    2.11
     පිළිබ
    2.10
     정의역
    2.00
    𝜁
    1.99
    淀
    1.97
    픕
    1.95
    Bhar
    1.94
    vaient
    1.91
    POSITIVE LOGITS
     personally
    1.50
     of
    1.47
     to
    1.42
     이
    1.37
     it
    1.35
     user
    1.31
    ijden
    1.29
    rians
    1.29
    erson
    1.27
     gives
    1.26
    Activations Density 0.000%

    No Known Activations