© 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. 7428
    Prev
    Next
    INDEX
    Explanations

    every, each, all

    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
     mainly
    1.13
     কিছুদিন
    1.10
     अपेक्षाकृत
    1.07
    mainly
    1.06
     Mainly
    1.05
    較
    1.03
    的一些
    1.01
    繼續
    1.01
    比較的
    1.01
    较
    0.98
    POSITIVE LOGITS
     every
    4.72
    every
    4.33
     Every
    4.18
    Every
    4.00
     EVERY
    3.96
    EVERY
    3.74
     ogni
    3.61
     setiap
    3.43
    每一个
    3.16
     каждую
    3.16
    Activations Density 0.674%

    No Known Activations