© 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. 1945
    Prev
    Next
    INDEX
    Explanations

    numbers and operations

    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
    |-\
    0.63
     usw
    0.59
     Sdn
    0.58
    歌手
    0.57
    이렇게
    0.57
    োজেন
    0.57
    |.
    0.56
    عبد
    0.55
     /,
    0.55
     Име
    0.54
    POSITIVE LOGITS
    ️⃣
    0.83
    ⃣
    0.81
    ви
    0.75
     تعالیٰ
    0.68
     wholesale
    0.67
    ចូល
    0.63
    
    0.63
     brought
    0.63
     unsettling
    0.62
    पिक्सल
    0.61
    Activations Density 0.386%

    No Known Activations