© 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. 86698
    Prev
    Next
    INDEX
    Explanations

    mixed-language specific nouns

    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
    The
    -1.64
    縠
    -1.62
    {
    -1.61
    黑色的
    -1.55
     твои
    -1.53
    為主
    -1.53
    '
    -1.53
     soigneusement
    -1.52
    熜
    -1.52
    你这个
    -1.52
    POSITIVE LOGITS
     our
    1.88
     singola
    1.78
     even
    1.64
    Boxscore
    1.55
     macchina
    1.55
     jika
    1.52
    باه
    1.48
     tempi
    1.46
     ancaman
    1.45
     giusta
    1.44
    Activations Density 0.023%

    No Known Activations