© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5447
    Prev
    Next
    INDEX
    Explanations

    The neuron flags second-person promotional or inspirational statements promising benefits (e.g. “you can experience… joy, health, and happiness”).

    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
     antitrust
    0.81
     আতঙ্ক
    0.77
     scoreboard
    0.74
    讨厌
    0.72
     policymakers
    0.70
    👔
    0.69
     punish
    0.69
     sportsbook
    0.67
     politician
    0.66
     employees
    0.65
    POSITIVE LOGITS
     Spiritual
    1.92
     Reiki
    1.91
    🕉
    1.87
    spiritual
    1.84
     meditation
    1.81
     Meditation
    1.80
     meditative
    1.80
     spiritual
    1.78
     Spirituality
    1.70
     spirituality
    1.69
    Activations Density 1.887%

    No Known Activations