© 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. 58960
    Prev
    Next
    INDEX
    Explanations

    zyg/zig/zym words

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

    The neuron strongly activates on tokens containing the “Zig”/“Zyg” letter sequence (words beginning with Z-i-g or Z-y-g).

    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
    کری
    -0.95
     Retrieval
    -0.75
     Mox
    -0.74
    างเกง
    -0.74
     Kuli
    -0.73
    ConstraintLayout
    -0.72
    ไข
    -0.72
     Celui
    -0.71
     رجال
    -0.70
     Contest
    -0.70
    POSITIVE LOGITS
     Zag
    1.10
    Zag
    1.06
     zag
    1.05
     Zig
    1.00
    zag
    0.94
     zig
    0.90
    zig
    0.87
    Zig
    0.81
     fotografía
    0.79
     зи
    0.74
    Activations Density 0.023%

    No Known Activations