© 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. 98477
    Prev
    Next
    INDEX
    Explanations

    wool and woolen products

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

    The neuron is keyed to mentions of wool or related textile fiber materials and processes.

    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
    compliant
    -0.73
    绣
    -0.72
    dox
    -0.71
     وزیر
    -0.69
    青木
    -0.68
    Gfx
    -0.68
     Silicone
    -0.68
     bois
    -0.68
    cotton
    -0.67
    WebControls
    -0.67
    POSITIVE LOGITS
     wool
    1.63
     Wool
    1.30
    Wool
    1.11
     fel
    1.02
     woolen
    0.96
     natural
    0.90
     greasy
    0.88
    メリ
    0.86
     Merino
    0.86
     Nuno
    0.86
    Activations Density 0.018%

    No Known Activations