© 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. 765
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to self-help and personal-development advice—especially imperatives about reading, building, or surrounding yourself with self-help books and resources.

    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
     Messrs
    0.77
     tonnage
    0.76
    招标
    0.71
    抢
    0.70
    公示
    0.67
     hydraul
    0.67
     showcase
    0.67
     மாநக
    0.67
     gavel
    0.67
    搶
    0.67
    POSITIVE LOGITS
     mindfulness
    2.41
     Mindfulness
    2.39
     meditation
    2.20
     Meditation
    2.13
     psychotherapy
    2.09
     meditative
    1.84
     meditations
    1.84
    Mental
    1.82
     journaling
    1.82
     medit
    1.81
    Activations Density 3.041%

    No Known Activations