© 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. 15971
    Prev
    Next
    INDEX
    Explanations

    level of

    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
    उथ
    2.88
     troppo
    2.47
    బాద్
    2.45
    ][:
    2.42
    ്ര
    2.34
    力
    2.32
    াবাদ
    2.31
    MainWindow
    2.28
    മൂഹ
    2.27
     pancre
    2.24
    POSITIVE LOGITS
    ஞ்ஞான
    2.10
     العليا
    2.09
    ited
    2.09
    oksatta
    2.08
    伍
    2.05
    ständig
    2.01
    ᴏ
    2.01
    <bos>
    1.99
     behold
    1.98
    بيب
    1.97
    Activations Density 0.086%

    No Known Activations