© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5723
    Prev
    Next
    INDEX
    Explanations

    LL followed by abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     Lisbon
    0.89
     Sparta
    0.86
     Krat
    0.84
     கிரேக்க
    0.82
    捷
    0.80
     Krypt
    0.79
    Bruno
    0.79
    苫
    0.79
     Leicester
    0.79
     zeolite
    0.79
    POSITIVE LOGITS
     LL
    1.63
    LL
    1.57
    mm
    1.50
     mm
    1.42
     dd
    1.37
     MM
    1.36
    dd
    1.31
    MM
    1.30
    ll
    1.29
     SS
    1.28
    Activations Density 0.286%

    No Known Activations