© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50259
    Prev
    Next
    INDEX
    Explanations

    ordering and layout

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

    The neuron fires on technical configuration and parameter keywords (e.g. “Depth,” “Major,” “Width,” “NEON,” “optimized,” “sources,” “packing”) used as section headings or option names in low-level hardware/software specifications.

    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
    unsaturated
    -0.75
     komplex
    -0.72
    panjang
    -0.72
     teraz
    -0.71
     CHRIST
    -0.67
    gradient
    -0.66
     tien
    -0.66
    ХО
    -0.66
     ressort
    -0.65
     bine
    -0.64
    POSITIVE LOGITS
     order
    1.17
     ordering
    1.03
    Order
    1.02
    ZY
    0.98
    order
    0.98
     Layout
    0.96
    ORDER
    0.96
    Row
    0.95
    getLayout
    0.94
     row
    0.93
    Activations Density 0.025%

    No Known Activations