© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4377
    Prev
    Next
    INDEX
    Explanations

    explanation and solution improvements

    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
     shaped
    1.08
     гиб
    1.04
     governing
    1.02
     belonging
    1.02
     govern
    1.02
     governed
    1.00
    )_{(
    1.00
    ประชาชน
    1.00
    gover
    1.00
     disruptions
    0.99
    POSITIVE LOGITS
    してもら
    0.99
    彼は
    0.95
    告诉我
    0.93
    まぁ
    0.92
    念
    0.92
     Fawcett
    0.88
     fez
    0.87
     꺼
    0.87
     আমাদেরকে
    0.85
    给我
    0.85
    Activations Density 0.583%

    No Known Activations