© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62656
    Prev
    Next
    INDEX
    Explanations

    police and public safety training

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     badge
    -0.78
     department
    -0.76
    badge
    -0.73
     нарушения
    -0.72
    Superintendent
    -0.71
    manya
    -0.71
     vuelto
    -0.69
     Superintendent
    -0.68
    lanta
    -0.67
    लों
    -0.66
    POSITIVE LOGITS
     Criminal
    0.98
     police
    0.94
    Sheriff
    0.91
     Police
    0.91
     academies
    0.84
    Police
    0.83
     Law
    0.83
    Law
    0.82
     POLICE
    0.81
    FBI
    0.80
    Activations Density 0.031%

    No Known Activations