© 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. 11156
    Prev
    Next
    INDEX
    Explanations

    Middle East

    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
    肩
    2.35
    apun
    2.28
    !/"
    2.26
    िवे
    2.24
    ğun
    2.19
    agel
    2.18
    愿意
    2.16
     iyi
    2.16
     karenge
    2.16
    oula
    2.14
    POSITIVE LOGITS
    ්
    2.84
     grudge
    2.76
    ^[
    2.64
     spec
    2.48
    𝗘
    2.47
     ח
    2.46
     ディ
    2.45
     א
    2.34
    ים
    2.28
    阿拉伯
    2.28
    Activations Density 0.015%

    No Known Activations