© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15741
    Prev
    Next
    INDEX
    Explanations

    spiritual awareness and meditation

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

    The neuron strongly activates on words and phrases that mark a first-person, self-reflective perspective—especially “I,” “my,” and verbs expressing personal feelings or thought.

    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_24_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
    噱
    0.89
     मिठाई
    0.89
    dataGridView
    0.85
    établ
    0.85
    Adidas
    0.84
    Nintendo
    0.80
    MLB
    0.80
    кугӀ
    0.80
    ล
    0.79
    Surprisingly
    0.79
    POSITIVE LOGITS
     Reiki
    1.30
     Spirituality
    1.27
     Spiritual
    1.26
     Shakti
    1.24
     Consciousness
    1.21
     relational
    1.17
     Integrative
    1.16
     Holistic
    1.15
     Swami
    1.13
     Emotional
    1.10
    Activations Density 1.238%

    No Known Activations