© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47341
    Prev
    Next
    INDEX
    Explanations

    consciousness and mental awareness

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

    The neuron fires strongly on mentions of “consciousness” (and related forms like “conscious” or “consciously”).

    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
     memoria
    -0.89
    inetics
    -0.84
    ientos
    -0.79
    umn
    -0.77
    飯
    -0.77
    imp
    -0.75
    cen
    -0.75
     quickly
    -0.74
     contextual
    -0.73
     vérité
    -0.71
    POSITIVE LOGITS
     consciousness
    2.17
    consciousness
    1.98
    Conscious
    1.88
     Consciousness
    1.80
     conscious
    1.74
     Conscious
    1.56
     consciente
    1.38
    conscious
    1.34
    意識
    1.32
     consciência
    1.32
    Activations Density 0.078%

    No Known Activations