© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35758
    Prev
    Next
    INDEX
    Explanations

    running with the ball

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    oggler
    0.54
    terer
    0.51
     canad
    0.51
    Aux
    0.50
     eyewear
    0.49
    нув
    0.49
    гну
    0.49
     गम
    0.47
    媇
    0.47
    畛
    0.46
    POSITIVE LOGITS
     serão
    0.57
     некоторы
    0.56
     नीति
    0.54
    ეცი
    0.54
     будут
    0.54
     --
    0.53
     são
    0.53
     दोन्ही
    0.53
     је
    0.52
     после
    0.52
    Activations Density 0.005%

    No Known Activations