© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91733
    Prev
    Next
    INDEX
    Explanations

    nuclear reactors

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

    The neuron strongly activates on numeric expressions—especially multi‐digit numbers and counts.

    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
     製造
    -0.79
    łyż
    -0.78
    zdjęcie
    -0.77
    名誉
    -0.77
     production
    -0.75
    诙
    -0.70
    engineer
    -0.70
    CTR
    -0.67
     kuning
    -0.67
     жі
    -0.67
    POSITIVE LOGITS
     reactors
    0.90
     passively
    0.80
    SERIAL
    0.79
     diseños
    0.77
     ebook
    0.77
     ニット
    0.77
     demonstr
    0.77
     Méndez
    0.76
     empêcher
    0.75
    ensions
    0.74
    Activations Density 0.017%

    No Known Activations