© 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. 29-GEMMASCOPE-2-RES-262K
    7. 145345
    Prev
    Next
    INDEX
    Explanations

    supplemental academic and technical terms

    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_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    यह
    0.96
    Eat
    0.94
    Alles
    0.90
    Hg
    0.88
    Buen
    0.87
    Give
    0.87
    Hoy
    0.86
    Whenever
    0.85
    •
    0.85
    Next
    0.83
    POSITIVE LOGITS
     homework
    0.89
     appendix
    0.81
     appendices
    0.80
     ספר
    0.75
     funzioni
    0.72
     Homework
    0.71
     teorie
    0.70
     Cinematic
    0.67
     employment
    0.66
     supplemental
    0.64
    Activations Density 0.000%

    No Known Activations