© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85262
    Prev
    Next
    INDEX
    Explanations

    width and height measurements

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

    width and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     женщин
    0.40
     பெண்கள்
    0.40
    нон
    0.37
    ยม
    0.37
    ktan
    0.36
    ｖ
    0.35
    畬
    0.34
    quement
    0.34
    橑
    0.34
     महिलाओ
    0.34
    POSITIVE LOGITS
     horizontal
    0.55
     width
    0.52
     horizontally
    0.52
     horizontale
    0.49
     husband
    0.49
     her
    0.45
     Horizontal
    0.45
     hor
    0.44
    horizontal
    0.43
     económicas
    0.42
    Activations Density 0.057%

    No Known Activations