© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1019
    Prev
    Next
    INDEX
    Explanations

    try for requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    鑄
    2.58
     밝
    2.40
    數量
    2.39
     فلم
    2.29
     알
    2.28
     색
    2.27
     건강
    2.26
     جانا
    2.26
     아
    2.26
    滯
    2.25
    POSITIVE LOGITS
     kegiatan
    2.19
     bentuk
    2.03
     berikutnya
    2.01
     daerah
    2.00
     segera
    2.00
     tingkat
    1.98
     pelaksanaan
    1.97
     tindakan
    1.94
     banyak
    1.94
     melakukan
    1.94
    Activations Density 0.089%

    No Known Activations