© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39035
    Prev
    Next
    INDEX
    Explanations

    simulator mode or interface

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

    The neuron detects mentions of “simulator” (and related simulator‐mode terms) in code or Q&A text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.73
    <bos>
    -1.63
     Unglück
    -1.56
     aktuellen
    -1.48
     damaligen
    -1.39
     Organisator
    -1.37
     Públicas
    -1.37
     including
    -1.34
    Grazie
    -1.34
     dolayı
    -1.30
    POSITIVE LOGITS
     Hồ
    1.74
     compagnies
    1.35
    ers
    1.31
    gggg
    1.30
     fêtes
    1.30
     fête
    1.29
     née
    1.27
    alike
    1.26
     VERS
    1.24
    HEAST
    1.24
    Activations Density 0.073%

    No Known Activations