© 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. 10-GEMMASCOPE-RES-131K
    7. 59775
    Prev
    Next
    INDEX
    Explanations

    states or occurrences

    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
     if
    -2.34
     There
    -2.17
     If
    -2.14
     AND
    -1.89
    There
    -1.88
     by
    -1.88
    To
    -1.88
     When
    -1.83
    左側
    -1.80
     wants
    -1.79
    POSITIVE LOGITS
     nimmer
    2.00
    鲠
    1.98
     vengono
    1.95
    呶
    1.94
     手帳
    1.92
    只是
    1.87
    皛
    1.84
     oogen
    1.80
    ーズン
    1.80
    我们
    1.80
    Activations Density 0.014%

    No Known Activations