© 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. 2846
    Prev
    Next
    INDEX
    Explanations

    different languages

    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
    y
    1.44
    ي
    1.32
    м
    1.28
    షి
    1.23
    ০
    1.19
    u
    1.17
    รั่ง
    1.17
    isati
    1.16
    s
    1.13
    ৮
    1.12
    POSITIVE LOGITS
    ،
    1.25
     ਅਤੇ
    1.21
     的
    1.18
    ؛
    1.18
     大
    1.17
    .[[
    1.14
    এবং
    1.13
     بالإضافة
    1.13
    ਨ
    1.12
    cycline
    1.10
    Activations Density 0.071%

    No Known Activations