© 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. 70316
    Prev
    Next
    INDEX
    Explanations

    she was ruled

    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
     if
    -2.23
     for
    -2.03
     when
    -1.78
    However
    -1.64
    If
    -1.55
    When
    -1.55
    Когда
    -1.49
    ViewChild
    -1.48
    Конечно
    -1.48
    although
    -1.42
    POSITIVE LOGITS
     gebruikt
    1.46
     básicamente
    1.42
     relies
    1.34
     contará
    1.34
    Kew
    1.33
    曖昧さ回避
    1.32
     aisladas
    1.31
     it
    1.30
    到处
    1.29
     várias
    1.27
    Activations Density 0.116%

    No Known Activations