© 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. 11822
    Prev
    Next
    INDEX
    Explanations

    virtual machines, Reality, Assistant, DOM

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

    The neuron detects references to “virtual” contexts or entities (e.g. virtual machines, virtual events, virtual networks).

    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
     precarious
    0.64
    dés
    0.59
     वेबसाईट
    0.58
     proportions
    0.57
    oyl
    0.56
     irradi
    0.55
    throughput
    0.55
    径
    0.54
     myst
    0.54
     webs
    0.54
    POSITIVE LOGITS
    助理
    0.70
    చర్
    0.68
     virtually
    0.62
     Virt
    0.60
    Vir
    0.59
    Virt
    0.58
    virt
    0.57
     toured
    0.55
     virt
    0.55
    Tourism
    0.54
    Activations Density 0.149%

    No Known Activations