© 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. 130955
    Prev
    Next
    INDEX
    Explanations

    transistor bipolar junction

    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
    〼
    -1.53
    ⩴
    -1.48
    鲠
    -1.44
    猻
    -1.41
     same
    -1.41
     justifyContent
    -1.41
    　(
    -1.38
    潯
    -1.37
     yake
    -1.36
    ोजन
    -1.36
    POSITIVE LOGITS
    '
    1.52
    ↵
    1.50
    的工作
    1.38
    ’
    1.28
     /
    1.23
    diseño
    1.23
     And
    1.21
    ссмо
    1.20
    !
    1.17
     могут
    1.15
    Activations Density 0.019%

    No Known Activations