© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15593
    Prev
    Next
    INDEX
    Explanations

    copyright protection and licensing

    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
    ibia
    2.11
     hypothalam
    2.02
     tangente
    1.95
    盆
    1.90
     উন্ন
    1.89
     undet
    1.88
    addGroup
    1.85
     приложение
    1.81
     sàng
    1.81
    স্তের
    1.79
    POSITIVE LOGITS
    t
    1.75
    s
    1.59
    rá
    1.48
     फिल्मों
    1.35
    tir
    1.33
    tik
    1.31
    tom
    1.29
     ​​
    1.27
    sour
    1.27
    tss
    1.27
    Activations Density 0.032%

    No Known Activations