© 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. 22-GEMMASCOPE-RES-131K
    7. 95789
    Prev
    Next
    INDEX
    Explanations

    area. bay. spot. wine. route

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ּוֹ
    -1.87
    ૉ
    -1.70
     موبایل
    -1.63
     familières
    -1.55
     оружи
    -1.48
    וּ
    -1.45
    ຣ
    -1.45
    作战
    -1.44
    ֶּ
    -1.44
     seçenek
    -1.41
    POSITIVE LOGITS
     ویتامین
    1.58
    TextButton
    1.41
    ׇ
    1.33
     acrylique
    1.30
     mainly
    1.29
     фильтр
    1.29
    ·
    1.25
     nine
    1.23
     other
    1.23
     has
    1.20
    Activations Density 0.052%

    No Known Activations