© 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. 10716
    Prev
    Next
    INDEX
    Explanations

    language fragments

    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
    ات
    2.37
    噌
    2.36
     Một
    2.18
     cobbled
    2.00
    ных
    2.00
    Một
    1.94
    わせて
    1.93
    സ്ഥ
    1.91
    sembled
    1.90
    .«
    1.90
    POSITIVE LOGITS
    عرف
    2.21
    germeister
    2.05
    kj
    2.04
    ৃত্তি
    2.02
    aros
    2.01
    l
    1.99
    dziel
    1.95
    tit
    1.95
    ká
    1.94
    正确
    1.92
    Activations Density 0.002%

    No Known Activations