© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10283
    Prev
    Next
    INDEX
    Explanations

    defining or importing code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hatta
    0.85
    дың
    0.83
    
    0.79
    ″
    0.78
    рования
    0.76
    рование
    0.75
    ◦
    0.75
     ר
    0.74
     ס
    0.74
     narrowed
    0.72
    POSITIVE LOGITS
    у
    1.01
    কে
    0.95
    ди
    0.93
    ン
    0.92
    дан
    0.92
    一个
    0.92
     nouă
    0.91
    ва
    0.88
    된
    0.87
    dataTable
    0.86
    Activations Density 0.972%

    No Known Activations