© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9859
    Prev
    Next
    INDEX
    Explanations

    directory or folder path

    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
     bå
    1.29
    嗓
    1.11
     Irland
    1.09
    舫
    1.06
    泳
    1.06
    oglob
    1.05
    pap
    1.05
    oneph
    1.04
    ύ
    1.04
    ypen
    1.01
    POSITIVE LOGITS
    フォルダ
    1.72
     mkdir
    1.64
    文件夹
    1.62
     subdirectory
    1.59
     directory
    1.54
    ディレクトリ
    1.54
     subdir
    1.51
     folder
    1.47
     basePath
    1.45
     dirs
    1.44
    Activations Density 0.088%

    No Known Activations