© 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. 35865
    Prev
    Next
    INDEX
    Explanations

    ratio, proportion, scale

    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
     Edad
    0.57
    <h4>
    0.52
     are
    0.51
    таў
    0.51
     vuos
    0.51
     IS
    0.50
    <unused244>
    0.50
     theologians
    0.49
     старије
    0.49
     ;;
    0.49
    POSITIVE LOGITS
    un
    0.65
    et
    0.58
    ed
    0.56
     ratio
    0.56
    Ratio
    0.54
    aggressive
    0.54
    existing
    0.53
    ر
    0.53
    olution
    0.53
    '
    0.52
    Activations Density 0.018%

    No Known Activations