© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9850
    Prev
    Next
    INDEX
    Explanations

    ethical and moral considerations

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

    The neuron is triggered by words and phrases that express moral or ethical judgment (e.g., wicked, moral, ethical).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     merak
    0.61
    ignac
    0.60
     Festa
    0.60
     diversification
    0.59
    掐
    0.57
     நில
    0.54
    멍
    0.54
     NASA
    0.54
    🎆
    0.54
    精彩
    0.54
    POSITIVE LOGITS
     ethical
    2.75
     ethics
    2.67
     moral
    2.64
     morality
    2.59
     morally
    2.56
     Ethical
    2.55
     Ethics
    2.50
    ethical
    2.50
     ethically
    2.48
    Ethics
    2.47
    Activations Density 0.425%

    No Known Activations