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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43777
    Prev
    Next
    INDEX
    Explanations

    fabric / fabrication

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

    The neuron activates on metaphorical terms for a woven or structured foundation—words like “fabric,” “tapestry,” “collective psyche,” and similar that describe the underlying structure of something.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </i>
    -1.82
    Qur
    -1.78
    猛地
    -1.70
    sukienka
    -1.69
    adalah
    -1.66
     nových
    -1.66
     modrá
    -1.63
     heridos
    -1.63
    我们
    -1.56
    DON
    -1.55
    POSITIVE LOGITS
     of
    2.13
    j
    1.71
    各大
    1.69
    man
    1.61
     He
    1.54
    国家的
    1.48
    ak
    1.48
     être
    1.46
    f
    1.40
    right
    1.38
    Activations Density 0.028%

    No Known Activations