© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10323
    Prev
    Next
    INDEX
    Explanations

    color followed by colon

    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_22_width_16k_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
    tic
    0.80
    favor
    0.79
    एगा
    0.76
     setObject
    0.76
    Colors
    0.75
     màu
    0.75
    asteroid
    0.75
    顺
    0.74
    tics
    0.74
     თან
    0.74
    POSITIVE LOGITS
    iune
    0.90
     সমিতি
    0.85
     Интернет
    0.81
    的基本
    0.80
     ชั่วโมง
    0.77
     wireless
    0.76
    സമയം
    0.74
    wireless
    0.74
     verein
    0.72
    اتو
    0.72
    Activations Density 0.006%

    No Known Activations