© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45631
    Prev
    Next
    INDEX
    Explanations

    product names

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

    The neuron detects mentions of specific commercial product or brand names (e.g., Etch-a-Sketch, Mr. Potato Head, Skittles, Alka-Seltzer, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    这是一
    -1.34
     alem
    -1.34
    ↵
    -1.34
     Câ
    -1.33
    清晨
    -1.26
     seco
    -1.23
    5
    -1.23
    8
    -1.22
    it
    -1.20
    </sup>
    -1.19
    POSITIVE LOGITS
     должны
    1.48
     Antrag
    1.43
     aún
    1.30
     Lengkap
    1.30
     všechny
    1.28
     reveló
    1.28
    hljs
    1.27
    dición
    1.27
     وتسجيلات
    1.26
    olescence
    1.24
    Activations Density 0.036%

    No Known Activations