© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2885
    Prev
    Next
    INDEX
    Explanations

    reducing negative impacts or quantities

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ت
    2.99
    ين
    2.87
    aide
    2.78
    नों
    2.76
     والمع
    2.74
    注意的是
    2.74
    ERN
    2.68
    itif
    2.67
    aq
    2.65
    alve
    2.60
    POSITIVE LOGITS
     $(<
    3.64
     thiểu
    3.04
    
    2.98
    
    2.66
    ↓↓
    2.63
    𝑘
    2.50
     charla
    2.49
    फारिश
    2.46
     thiệu
    2.45
    
    2.43
    Activations Density 0.336%

    No Known Activations