© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34504
    Prev
    Next
    INDEX
    Explanations

    court types

    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_22/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
    FOREWORD
    -1.29
    türk
    -1.27
     chrétienne
    -1.27
    madeus
    -1.26
    щики
    -1.22
    başı
    -1.21
    nější
    -1.20
     andra
    -1.20
     spiele
    -1.20
     tfsi
    -1.20
    POSITIVE LOGITS
    んでる
    1.46
     лекарства
    1.44
    áles
    1.41
    ͎
    1.40
     рецепта
    1.38
     дает
    1.34
     სა
    1.34
    憷
    1.30
     обычно
    1.30
     Olivenöl
    1.29
    Activations Density 0.243%

    No Known Activations