© 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. 49759
    Prev
    Next
    INDEX
    Explanations

    legal counts and commandments

    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
    Not in Any Lists

    No Comments

    Negative Logits
    il
    1.02
    g
    0.76
    an
    0.74
    o
    0.74
    and
    0.73
    op
    0.73
    even
    0.72
    such
    0.68
    different
    0.66
    i
    0.66
    POSITIVE LOGITS
     is
    0.68
     of
    0.67
     silenc
    0.64
    に
    0.64
     counts
    0.63
     для
    0.62
     troubleshooting
    0.61
     soluzioni
    0.59
     counted
    0.58
     circunst
    0.58
    Activations Density 0.001%

    No Known Activations