© 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. 10751
    Prev
    Next
    INDEX
    Explanations

    tailor these paragraphs

    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
     tweaked
    0.76
     ።
    0.74
    sers
    0.73
    oser
    0.72
    ⿳
    0.72
     besser
    0.72
    ্ধ
    0.72
    杷
    0.72
    菁
    0.71
    ن
    0.70
    POSITIVE LOGITS
    物质
    0.83
     испыта
    0.77
     Jeg
    0.77
    up
    0.75
    hours
    0.75
    创建一个
    0.75
     upoz
    0.74
     jeg
    0.73
     tartoz
    0.73
     தினமும்
    0.72
    Activations Density 0.018%

    No Known Activations