© 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. 79364
    Prev
    Next
    INDEX
    Explanations

    police and policing

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

    The neuron strongly activates on mentions of police or law-enforcement terms (e.g., “police,” “officers,” “policing,” “firearms”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
     army
    -0.81
     Lt
    -0.78
     CFD
    -0.76
    army
    -0.76
    armée
    -0.75
    Lt
    -0.73
     bailarina
    -0.72
     ARMY
    -0.72
    inę
    -0.72
    Army
    -0.71
    POSITIVE LOGITS
     operational
    0.96
     Operational
    0.87
     tutor
    0.78
     $)
    0.77
    intValue
    0.76
     Superintendent
    0.75
    paq
    0.72
    Superintendent
    0.71
    nungen
    0.71
    operational
    0.70
    Activations Density 0.016%

    No Known Activations