© 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. 7462
    Prev
    Next
    INDEX
    Explanations

    Federal Reserve

    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
    datum
    0.77
    もので
    0.75
     الحاس
    0.73
    ুর
    0.72
    흑
    0.72
    ੀਆਂ
    0.70
    몬
    0.70
    cut
    0.70
    挫
    0.69
    Hire
    0.68
    POSITIVE LOGITS
     Shia
    0.87
    спекти
    0.85
    ەیە
    0.81
     Autonomous
    0.80
     পুর
    0.79
     escena
    0.78
    apal
    0.77
     Jir
    0.76
     Sis
    0.76
     ga
    0.76
    Activations Density 0.061%

    No Known Activations