© 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. 34-GEMMASCOPE-RES-131K
    7. 106700
    Prev
    Next
    INDEX
    Explanations

    quantum electrodynamics diamond NV emitters

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

    The neuron fires on highly specialized scientific and engineering terminology—particularly advanced physics/quantum‐optics device and materials names (e.g. “nitrogen vacancies,” “memristors,” “optical microresonators,” “single‐photon generation,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    复制
    -0.76
     especias
    -0.74
     anos
    -0.73
    DESCRIPTION
    -0.71
     pleaded
    -0.70
     Alerts
    -0.69
     sons
    -0.69
    Screen
    -0.69
     tribes
    -0.69
    Explanation
    -0.68
    POSITIVE LOGITS
     NV
    1.05
     diamond
    0.91
     readout
    0.88
    NV
    0.86
     Initialization
    0.86
     emitter
    0.83
    diamond
    0.80
    Susanne
    0.79
    Cá
    0.77
    Refriger
    0.76
    Activations Density 0.083%

    No Known Activations