© 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. 20734
    Prev
    Next
    INDEX
    Explanations

    description of text segments

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

    The neuron is keyed to mentions of food items, menus, and their quality (especially “gluten-free” offerings and related descriptors) in restaurant reviews.

    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
     kompeti
    -1.77
    ならば
    -1.59
     แท้
    -1.52
    の世界
    -1.52
     dilaksanakan
    -1.51
    гти
    -1.51
     praktis
    -1.48
    Following
    -1.48
     digelar
    -1.48
    笑了笑
    -1.46
    POSITIVE LOGITS
    𓁹
    2.05
     baloncesto
    1.75
     męski
    1.71
    叕
    1.70
     overall
    1.68
     také
    1.66
     τοῦ
    1.61
     are
    1.61
    zések
    1.58
    我们是
    1.56
    Activations Density 0.586%

    No Known Activations