© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2384
    Prev
    Next
    INDEX
    Explanations

    ways to improve

    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_65k_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
    avu
    1.51
     Cato
    1.51
     tačiau
    1.42
     Ols
    1.39
    ada
    1.35
     Additionally
    1.34
    َي
    1.33
    ܨ
    1.33
    يًا
    1.32
    ız
    1.31
    POSITIVE LOGITS
    文書
    1.36
     sue
    1.31
    薦
    1.28
    THAT
    1.28
    corto
    1.26
     stroj
    1.25
    cure
    1.25
     partito
    1.24
    やる
    1.23
    乜
    1.22
    Activations Density 0.001%

    No Known Activations