© 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. 187162
    Prev
    Next
    INDEX
    Explanations

    multilingual content

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

    political divisions

    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
    ма
    0.54
    тво
    0.48
    кі
    0.47
    بة
    0.46
     precluded
    0.45
    frigerator
    0.45
    naires
    0.45
    itherto
    0.45
    т
    0.44
     mendengar
    0.43
    POSITIVE LOGITS
    不变
    0.50
    参数向量
    0.46
     తగ్
    0.45
     该
    0.44
     Пусть
    0.44
     ધાર
    0.43
    啮
    0.43
     సర్
    0.43
     旧
    0.43
    తర
    0.43
    Activations Density 0.001%

    No Known Activations