© 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. 75843
    Prev
    Next
    INDEX
    Explanations

    weave, weaver, woven

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

    The neuron fires on any token containing the letter sequence “weav” (e.g. Weaver, weave, weaving, waeve).

    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
    =>{
    -0.93
     Godt
    -0.79
     lương
    -0.74
     Provin
    -0.74
     ライ
    -0.73
     двига
    -0.73
    bilecek
    -0.72
     Vara
    -0.72
     reasonable
    -0.71
     consul
    -0.71
    POSITIVE LOGITS
     weaving
    1.39
     Wea
    1.37
    Wea
    1.30
     weave
    1.30
    wea
    1.27
    thread
    1.21
    Weaver
    1.17
    weave
    1.16
     Weaver
    1.15
     thread
    1.10
    Activations Density 0.017%

    No Known Activations