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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 581
    Prev
    Next
    INDEX
    Explanations

    torture

    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
     in
    -1.54
     about
    -1.52
     regarding
    -1.51
     information
    -1.45
     possessing
    -1.38
     lacking
    -1.34
    详解
    -1.33
     numerous
    -1.30
     encompassing
    -1.29
     dabar
    -1.27
    POSITIVE LOGITS
    (;;)
    1.59
    และ
    1.56
     épisode
    1.55
     vraiment
    1.52
    های
    1.50
     وم
    1.47
     également
    1.47
     essas
    1.46
     GenerationType
    1.45
    others
    1.45
    Activations Density 0.015%

    No Known Activations