© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5237
    Prev
    Next
    INDEX
    Explanations

    core part of a concept

    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_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     (
    0.86
    .)
    0.72
     или
    0.70
     ك
    0.69
    .
    0.67
    בד
    0.66
    นั้น
    0.66
    0.65
    峙
    0.65
     typename
    0.65
    POSITIVE LOGITS
    <unused1856>
    0.86
    <unused415>
    0.86
     yıllık
    0.85
    <unused412>
    0.85
    䫝
    0.84
     tradizionale
    0.83
    <unused1122>
    0.83
    лови
    0.82
    <unused781>
    0.82
    <unused149>
    0.82
    Activations Density 0.200%

    No Known Activations