© 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. 20239
    Prev
    Next
    INDEX
    Explanations

    expressing intent or purpose

    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
    中身
    -1.71
    詳細は
    -1.64
    関する
    -1.52
    选择了
    -1.48
    詳しくは
    -1.42
    livé
    -1.41
    НАЯ
    -1.39
    二日
    -1.39
     legger
    -1.39
     vestir
    -1.38
    POSITIVE LOGITS
     to
    3.33
     aim
    1.52
     aims
    1.48
     not
    1.47
     intended
    1.45
     is
    1.45
     goal
    1.44
     предназна
    1.43
     intent
    1.39
     purpose
    1.37
    Activations Density 0.240%

    No Known Activations