© 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. 56083
    Prev
    Next
    INDEX
    Explanations

    environmental and social responsibility

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

    The neuron detects high-level sustainability and social responsibility terms, especially “environmental,” “social,” and related corporate-responsibility language.

    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
    environmental
    -2.16
     environmental
    -2.06
     ENVIRONMENTAL
    -1.91
    Environmental
    -1.82
     Environmental
    -1.82
     environmentally
    -1.79
     экологи
    -1.63
    环保
    -1.56
    ENVIRONMENTAL
    -1.51
    environment
    -1.37
    POSITIVE LOGITS
     health
    1.36
     energy
    1.12
     biodiversity
    1.05
     noise
    0.91
     resource
    0.89
     species
    0.88
     water
    0.88
     social
    0.86
     habitat
    0.86
     recurso
    0.85
    Activations Density 0.037%

    No Known Activations