© 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. 2152
    Prev
    Next
    INDEX
    Explanations

    pick and choose

    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
    тых
    1.03
     attempts
    0.91
     цент
    0.90
    תיים
    0.89
    प्ताहिक
    0.88
     мах
    0.88
     걸
    0.87
    
    0.87
    려는
    0.86
    ாரம்
    0.85
    POSITIVE LOGITS
     wisely
    1.68
     parmi
    1.58
     lọc
    1.56
     dentre
    1.50
     picking
    1.40
     lựa
    1.39
    肢
    1.38
     quarrel
    1.34
    合适的
    1.33
    selectedIndex
    1.28
    Activations Density 0.159%

    No Known Activations