© 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. 22-GEMMASCOPE-2-RES-65K
    7. 7018
    Prev
    Next
    INDEX
    Explanations

    quantities and structures

    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_65k_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
     إلى
    0.81
     څخه
    0.74
    FromThe
    0.74
     থেকে
    0.72
    奻
    0.71
     গুরুত্বপূর্ণ
    0.70
    鉅
    0.69
    から
    0.69
    出来的
    0.69
     नाराज
    0.69
    POSITIVE LOGITS
     via
    1.12
     faster
    1.04
     посредством
    1.04
     quicker
    1.04
    然后再
    1.03
    វិញ
    1.01
     tramite
    1.00
    via
    0.99
    的过程中
    0.97
     mediante
    0.85
    Activations Density 0.178%

    No Known Activations