© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6534
    Prev
    Next
    INDEX
    Explanations

    negotiations and settlements

    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
    Negative Logits
    defence
    0.98
     Defence
    0.97
     totalitarian
    0.94
     defence
    0.94
    蔑
    0.93
     Defensa
    0.87
     solidar
    0.87
    捍
    0.87
     solidarity
    0.86
     unanim
    0.86
    POSITIVE LOGITS
     mediator
    1.04
     paz
    0.97
     mediators
    0.96
     peace
    0.96
     restorative
    0.94
     Annapolis
    0.92
     mediating
    0.91
     mediation
    0.90
     mediate
    0.89
     finne
    0.88
    Activations Density 0.109%

    No Known Activations