© 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. 4626
    Prev
    Next
    INDEX
    Explanations

    European empires and kingdoms

    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
     múltiples
    0.71
     jeśli
    0.69
     nível
    0.66
     ইন
    0.64
    <unused436>
    0.64
     contaminación
    0.63
     często
    0.63
     Jeśli
    0.62
     tenha
    0.61
    <unused99>
    0.61
    POSITIVE LOGITS
     Habsburg
    0.61
     Prussia
    0.60
     Serikat
    0.60
     Prussian
    0.59
    ussia
    0.59
    )"
    0.58
    ドイツ
    0.58
     annexed
    0.58
     monarchy
    0.58
     Austria
    0.57
    Activations Density 0.036%

    No Known Activations