© 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-16K
    7. 9720
    Prev
    Next
    INDEX
    Explanations

    templates for content generation

    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_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
    ا
    2.36
    ர
    2.33
    sled
    2.04
    رت
    1.99
     justifica
    1.98
    상
    1.94
    恍
    1.93
    ოლ
    1.92
    ه‌ای
    1.90
    ">⁡</
    1.87
    POSITIVE LOGITS
     Templates
    2.38
    ClCompile
    2.31
    _.
    2.28
    eyim
    2.26
     templates
    2.21
    PAR
    2.19
    লিত
    2.13
    ilh
    2.09
    elope
    2.08
    ើយ
    2.06
    Activations Density 0.061%

    No Known Activations