© 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. 13611
    Prev
    Next
    INDEX
    Explanations

    virtual, immersive

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

    The main thing this neuron does is detect mentions of Nintendo or Nintendo game worlds and related iconic franchises.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    immersive or imaginative experiences, particularly references to entertainment, fantasy worlds, and simulated environments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to imagined or alternate worlds—fantasy, virtual/parallel realities, and being transported into them.

    oai_token-act-pair · gpt-5Triggered 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
     salmon
    0.55
     Antioxid
    0.52
    粗
    0.51
     RAX
    0.51
     lightening
    0.51
     definitive
    0.50
    ceph
    0.50
     Salmon
    0.49
     नामांकन
    0.49
     definitivo
    0.49
    POSITIVE LOGITS
     imaginary
    2.19
     fictional
    2.08
     fictitious
    2.02
     काल्पनिक
    1.97
    虚拟
    1.93
     виртуа
    1.88
    仮想
    1.88
     simulated
    1.88
     imagined
    1.86
     fict
    1.86
    Activations Density 0.771%

    No Known Activations