© 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. 123849
    Prev
    Next
    INDEX
    Explanations

    numbers and prices

    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_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
     entonces
    -1.61
    儘
    -1.35
     Ideally
    -1.29
    絎
    -1.29
    นอก
    -1.29
     Needless
    -1.27
     інших
    -1.27
     escuelas
    -1.27
     různých
    -1.27
     luego
    -1.24
    POSITIVE LOGITS
    沇
    1.30
     dina
    1.29
    thed
    1.28
    鍇
    1.25
    骓
    1.24
     奈
    1.23
    ktur
    1.22
    bę
    1.22
     unserer
    1.20
     shipment
    1.20
    Activations Density 0.052%

    No Known Activations