© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2678
    Prev
    Next
    INDEX
    Explanations

    savings, discounts, research, usage

    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
     소프트
    1.08
    意大利
    1.03
    墨西哥
    1.01
    셸
    0.98
     bleed
    0.95
    扔
    0.95
     피
    0.92
     Charlottesville
    0.91
    盔
    0.91
     不同
    0.91
    POSITIVE LOGITS
     Indonesia
    2.40
     sudah
    2.24
     Indonesian
    2.20
    Indonesia
    2.12
     Indones
    2.07
     dapat
    2.00
     sesuai
    2.00
     tahun
    1.98
     hanya
    1.97
     Jakarta
    1.97
    Activations Density 0.014%

    No Known Activations