© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1086
    Prev
    Next
    INDEX
    Explanations

    code structure and operators

    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
    পূর্ন
    1.79
    Tras
    1.63
     ছিলোনা
    1.61
    അ
    1.59
    Tak
    1.59
    Ham
    1.58
    Ever
    1.57
    ėj
    1.54
    atribut
    1.54
    CAD
    1.53
    POSITIVE LOGITS
     也
    2.39
     啊
    2.37
     的
    2.31
     值
    2.28
     哦
    2.26
     而
    2.22
     然后
    2.22
     然而
    2.17
     因此
    2.16
     你
    2.14
    Activations Density 1.058%

    No Known Activations