© 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. 15959
    Prev
    Next
    INDEX
    Explanations

    baby meat, bear Arms, Law of

    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
     ottimo
    0.94
    aleph
    0.93
    ي
    0.90
    বিট
    0.89
    Explore
    0.88
    ર
    0.86
     cung
    0.86
    არე
    0.85
    ksi
    0.85
    فضل
    0.85
    POSITIVE LOGITS
     относя
    0.90
    teger
    0.88
     Neither
    0.86
     第
    0.86
     தொ
    0.86
     Last
    0.85
    льности
    0.85
     Pigs
    0.84
     соответственно
    0.84
    第六
    0.84
    Activations Density 0.000%

    No Known Activations