© 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. 34-GEMMASCOPE-RES-131K
    7. 4270
    Prev
    Next
    INDEX
    Explanations

    court case identifiers

    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_34/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
    Возраст
    -0.82
     inaug
    -0.82
    Polizei
    -0.81
    ändigen
    -0.80
     dikem
    -0.79
    ἓ
    -0.79
    ifornie
    -0.78
    Questão
    -0.78
    絅
    -0.77
     ціка
    -0.77
    POSITIVE LOGITS
    惊
    0.88
     geslacht
    0.82
    提起
    0.78
    двига
    0.78
    ూ
    0.77
     تج
    0.77
     cojín
    0.77
    플
    0.77
    со
    0.75
     exhale
    0.75
    Activations Density 0.048%

    No Known Activations