© 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. 551
    Prev
    Next
    INDEX
    Explanations

    docker.com/learn or products

    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
     ちゃっ
    2.58
     聞い
    2.54
    뷊
    2.54
     HUOBI
    2.51
     下さい
    2.48
     yên
    2.48
     பாபிலோ
    2.48
     Hoàng
    2.47
     ι
    2.46
     kttt
    2.45
    POSITIVE LOGITS
    ing
    1.58
    a
    1.49
    get
    1.39
    es
    1.38
    ↵↵
    1.37
    of
    1.36
    item
    1.36
    ↵
    1.34
    o
    1.32
    ed
    1.32
    Activations Density 0.018%

    No Known Activations