© 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. 41937
    Prev
    Next
    INDEX
    Explanations

    measurements and descriptions

    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
    Kemudian
    -1.54
    Meskipun
    -1.48
    Namun
    -1.48
    Since
    -1.45
     eleições
    -1.45
    Sementara
    -1.44
    сль
    -1.41
    Bahkan
    -1.39
    Sedangkan
    -1.39
     Meilleures
    -1.38
    POSITIVE LOGITS
    '
    2.05
    正常的
    1.69
     подготовка
    1.56
     печени
    1.54
     profundos
    1.49
     Männern
    1.47
     its
    1.45
     schaff
    1.45
    :'
    1.41
     You
    1.38
    Activations Density 0.044%

    No Known Activations