© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31486
    Prev
    Next
    INDEX
    Explanations

    IU, uterine, IUGR, growth

    np_acts-logits-general · gemini-2.5-flash-lite

    abbreviations and acronyms related to academic and medical institutions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    čki
    -0.76
    idoo
    -0.75
    :{
    -0.73
    arth
    -0.71
     Pand
    -0.70
     recuerda
    -0.69
    лыми
    -0.69
    umal
    -0.69
     zile
    -0.69
     دوم
    -0.69
    POSITIVE LOGITS
    wość
    0.79
    iligt
    0.76
    不说
    0.73
     IU
    0.70
     obstet
    0.68
    juice
    0.67
     rehearing
    0.66
    演
    0.66
    مود
    0.65
     gour
    0.65
    Activations Density 0.015%

    No Known Activations