© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11599
    Prev
    Next
    INDEX
    Explanations

    therefore,

    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
    ر
    3.67
    െ
    3.18
    특별시
    3.17
    症
    3.13
    ので
    3.01
    
    2.97
    ا
    2.94
    𝙔
    2.90
    ுற
    2.85
    ,{\
    2.82
    POSITIVE LOGITS
    s
    4.86
    ات
    4.44
    ের
    3.60
    ع
    3.55
    น
    3.34
    اته
    3.13
    т
    2.83
    น้อง
    2.83
    יות
    2.81
    ség
    2.79
    Activations Density 0.035%

    No Known Activations