© 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. 65734
    Prev
    Next
    INDEX
    Explanations

    breathable mesh upper

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

    The neuron fires on specific product identifiers, brand/model names, and technical footwear‐related terms.

    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
    länder
    -0.76
    Sheffield
    -0.75
     slab
    -0.72
    Né
    -0.71
    椎
    -0.71
     vertebrae
    -0.70
     Balk
    -0.70
     slabs
    -0.69
    Slab
    -0.69
     Kä
    -0.68
    POSITIVE LOGITS
     upper
    2.17
    upper
    1.71
     Upper
    1.56
    Upper
    1.51
     UPPER
    1.41
    UPPER
    1.23
     shoe
    1.20
    shoe
    1.15
     shoes
    1.13
     mesh
    1.13
    Activations Density 0.017%

    No Known Activations