© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12449
    Prev
    Next
    INDEX
    Explanations

    cybrary.it

    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
     آموزش
    1.92
     你
    1.92
     构建
    1.87
     관한
    1.83
    ោង
    1.77
     功能
    1.77
     อังกฤษ
    1.76
     Μ
    1.72
     文件
    1.72
     برند
    1.70
    POSITIVE LOGITS
     Estadual
    1.80
    以上に
    1.78
     maior
    1.71
     istri
    1.71
     principale
    1.68
    mente
    1.63
     Amelia
    1.62
     Selena
    1.62
     ebenfalls
    1.61
    決して
    1.60
    Activations Density 0.006%

    No Known Activations