© 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. 56379
    Prev
    Next
    INDEX
    Explanations

    multilingual

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

    path, Google, storage

    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
    सम्
    0.45
     bales
    0.44
    ac
    0.40
     present
    0.38
     cone
    0.38
     apes
    0.38
     threat
    0.37
     she
    0.37
     hydrophobic
    0.37
    {
    0.37
    POSITIVE LOGITS
    ง่าย
    0.50
     ક્ષ
    0.47
     درسنا
    0.47
     چیمپ
    0.47
     बहाल
    0.47
     десятки
    0.46
     навіть
    0.46
     حتی
    0.46
     পুনরুদ্ধার
    0.45
     області
    0.45
    Activations Density 0.000%

    No Known Activations