© 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. 13946
    Prev
    Next
    INDEX
    Explanations

    batch normalization, batch size

    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
    突出
    2.28
    akey
    2.28
    صله
    2.25
    orks
    2.21
    anson
    2.06
    긍
    2.02
    页面存档备份
    2.01
    oded
    2.00
    ॉ
    1.99
    ყო
    1.99
    POSITIVE LOGITS
    tus
    3.33
    d
    3.14
    র
    3.13
    ल
    3.02
    nltk
    3.00
    teries
    2.82
    ยนตร์
    2.81
    ะ
    2.78
    hock
    2.78
    zil
    2.76
    Activations Density 0.003%

    No Known Activations