© 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-65K
    7. 2110
    Prev
    Next
    INDEX
    Explanations

    summaries and explanations of topics

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    因为
    0.69
    izos
    0.68
     koska
    0.67
     etc
    0.66
     mivel
    0.66
    甚至
    0.64
    ),\
    0.63
     puisque
    0.63
     itd
    0.62
    辈
    0.62
    POSITIVE LOGITS
     Explained
    2.08
     Revisited
    1.84
     Overview
    1.77
     explained
    1.73
     Basics
    1.67
     revisited
    1.67
    Explained
    1.61
     overview
    1.54
     Fundamentals
    1.53
     expliqué
    1.45
    Activations Density 0.564%

    No Known Activations