© 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. 2747
    Prev
    Next
    INDEX
    Explanations

    division by

    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
     불구하고
    3.62
     opsi
    2.70
    ्रिक
    2.69
    ल्तान
    2.69
    Believe
    2.54
     nä
    2.53
    ق
    2.52
     persecution
    2.50
     opcion
    2.49
     pä
    2.47
    POSITIVE LOGITS
    ان
    3.75
    n
    3.36
    esity
    3.02
    ur
    2.98
    ла
    2.95
    娩
    2.92
     முறையில்
    2.86
    nun
    2.78
    ná
    2.76
     уж
    2.75
    Activations Density 0.143%

    No Known Activations