© 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. 17-GEMMASCOPE-2-RES-16K
    7. 8700
    Prev
    Next
    INDEX
    Explanations

    breaking down or summarizing information

    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_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    performing
    0.96
    maintenance
    0.94
    automated
    0.92
     ощущения
    0.91
     builtin
    0.87
    doing
    0.87
    glichen
    0.86
     தான
    0.86
    犒
    0.86
     mindless
    0.85
    POSITIVE LOGITS
     연구
    0.99
    연구
    0.89
     Italy
    0.88
     International
    0.86
     researched
    0.84
     confirmé
    0.84
     Research
    0.83
    消息
    0.83
     Import
    0.82
     Africa
    0.82
    Activations Density 0.116%

    No Known Activations