© 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. 1817
    Prev
    Next
    INDEX
    Explanations

    This neuron detects forward-looking, strategic vocabulary—terms related to anticipating, imagining, and planning for the future.

    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
     cosplay
    0.77
     splurge
    0.76
     vlak
    0.73
     underwhelming
    0.72
     blå
    0.72
     billionaire
    0.71
    年纪
    0.71
    噱
    0.71
    хие
    0.71
    趋势
    0.70
    POSITIVE LOGITS
     cognitive
    1.10
     Situated
    1.05
     situated
    1.05
     cognit
    1.05
     contexts
    1.04
     Cognitive
    1.01
     metac
    1.00
     mediates
    0.99
     mediating
    0.98
     mediated
    0.96
    Activations Density 0.657%

    No Known Activations