© 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. 6762
    Prev
    Next
    INDEX
    Explanations

    游戏 (game) 科技 (technology) 咸 (salty)

    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
    <unused1847>
    2.91
    <unused732>
    2.89
     functioning
    2.89
     buzzing
    2.88
    <unused298>
    2.84
     sprawling
    2.84
    <unused162>
    2.81
    <unused1703>
    2.80
    <unused1657>
    2.80
    ufieurs
    2.79
    POSITIVE LOGITS
    大
    3.08
    本
    3.04
    人
    2.96
    小
    2.90
    三
    2.89
    有
    2.88
    新
    2.85
    上
    2.83
    行
    2.82
    其
    2.80
    Activations Density 0.023%

    No Known Activations