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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30550
    Prev
    Next
    INDEX
    Explanations

    environmental racism justice

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

    content related to environmental pollution, contamination, and health impacts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of environmental contamination or hazards—especially references to pesticides, chemical exposures, and related pollution contexts.

    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
    esez
    -0.97
     đà
    -0.79
     ALCOHOL
    -0.78
    destructive
    -0.77
    struktur
    -0.75
    罂
    -0.75
     frutti
    -0.74
     signore
    -0.74
     casal
    -0.74
     preservatives
    -0.74
    POSITIVE LOGITS
     disproportion
    1.37
     EJ
    1.26
    EJ
    1.19
     communities
    1.18
     justice
    1.11
     asthma
    1.00
     burden
    0.98
     justicia
    0.98
     overburden
    0.97
     Asthma
    0.90
    Activations Density 0.012%

    No Known Activations