© 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. 2682
    Prev
    Next
    INDEX
    Explanations

    way that

    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
    Not in Any Lists

    No Comments

    Negative Logits
    s
    3.62
    epochs
    3.28
     самое
    3.11
    ات
    3.08
    ों
    2.98
    蒡
    2.91
     pared
    2.91
     brakes
    2.83
    髏
    2.82
     мне
    2.77
    POSITIVE LOGITS
    yyyy
    3.69
    yyyyyyyy
    3.50
    ので
    3.48
    ுங்கள்
    3.37
    ward
    3.25
    lı
    3.23
    িত্ব
    2.94
    yı
    2.92
    حية
    2.91
    y
    2.88
    Activations Density 0.163%

    No Known Activations