© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103872
    Prev
    Next
    INDEX
    Explanations

    policing practices

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

    The neuron detects mentions of police organizations—especially formal “Police Department” or similar agency names.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     considerado
    -0.79
     charged
    -0.71
     hvert
    -0.71
    Checksum
    -0.70
     dust
    -0.70
     dimulai
    -0.70
     ash
    -0.67
     charges
    -0.66
    éta
    -0.66
    赑
    -0.66
    POSITIVE LOGITS
     policing
    2.30
     Policing
    1.60
     patrolling
    1.23
     police
    1.06
     community
    1.04
     Community
    1.01
    community
    1.00
    Community
    0.99
     patrols
    0.90
    COMMUNITY
    0.89
    Activations Density 0.027%

    No Known Activations