© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104469
    Prev
    Next
    INDEX
    Explanations

    measure, mu, matrix

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

    The neuron fires on occurrences of mathematical “measure” terms—e.g. the word measure or measure‐symbols like μ or ν.

    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
     but
    -1.56
    砹
    -1.44
    /',
    -1.34
     院
    -1.34
     ингреди
    -1.34
     What
    -1.34
     quién
    -1.32
     района
    -1.32
    事態
    -1.30
    棰
    -1.30
    POSITIVE LOGITS
     ſy
    1.41
     福袋
    1.34
     of
    1.33
     yetu
    1.26
     剤
    1.26
     LOADING
    1.23
     ibang
    1.23
     icke
    1.21
     baada
    1.21
     nzuri
    1.20
    Activations Density 0.017%

    No Known Activations