© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3731
    Prev
    Next
    INDEX
    Explanations

    US states

    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
    laşt
    2.23
     aru
    2.10
    ्रेडिट
    2.02
     applauded
    2.01
    テー
    1.99
    rothed
    1.97
    ไทย
    1.96
    🎌
    1.93
     নিন্দা
    1.93
    romet
    1.93
    POSITIVE LOGITS
     Connecticut
    2.05
    겹
    1.90
    ிர
    1.88
     ব্যক্তি
    1.87
     Kaliforn
    1.84
     mism
    1.82
     ভরা
    1.80
     California
    1.80
     Illinois
    1.78
     Wisconsin
    1.78
    Activations Density 0.205%

    No Known Activations