© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13140
    Prev
    Next
    INDEX
    Explanations

    assembly instruction `rep`

    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
    <bos>
    4.24
    에
    2.63
    اخت
    2.58
    ი
    2.50
    ności
    2.48
    ம்
    2.47
    ه
    2.46
    !='
    2.41
    小程序
    2.36
    mkdirs
    2.35
    POSITIVE LOGITS
    YD
    2.62
    rage
    2.62
    𝐡
    2.58
    𝐆
    2.57
    strings
    2.54
    st
    2.50
    います
    2.47
    𝐞
    2.46
    mode
    2.43
    lil
    2.39
    Activations Density 0.033%

    No Known Activations