© 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. 105221
    Prev
    Next
    INDEX
    Explanations

    specific phrase starts

    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
     it
    -2.16
     ДЛЯ
    -1.48
     to
    -1.46
     食事
    -1.46
     Даже
    -1.46
     состоит
    -1.45
     by
    -1.37
     должен
    -1.37
    を行い
    -1.35
     mêmes
    -1.34
    POSITIVE LOGITS
    CRIPTION
    1.71
    chläge
    1.62
    The
    1.51
     معمول
    1.44
     fabrik
    1.44
     ofta
    1.42
    álise
    1.36
    𓐍
    1.36
    的产品
    1.36
    ца
    1.35
    Activations Density 0.000%

    No Known Activations