© 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. 56008
    Prev
    Next
    INDEX
    Explanations

    law enforcement deaths

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

    The neuron strongly responds to mentions of police or law‐enforcement contexts (e.g. “Police,” “officers,” “funerals”).

    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
     bij
    -0.79
    CDR
    -0.77
     âge
    -0.75
     Playhouse
    -0.75
     urodz
    -0.74
    湮
    -0.73
    QUENCE
    -0.72
     Konflikt
    -0.71
     lå
    -0.71
    tismo
    -0.70
    POSITIVE LOGITS
    Fallen
    1.08
     Fallen
    0.97
     departments
    0.96
     brotherhood
    0.96
     LEO
    0.92
     fallen
    0.91
    Badge
    0.89
     ambush
    0.88
     retreats
    0.86
     protectors
    0.84
    Activations Density 0.033%

    No Known Activations