© 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. 2048
    Prev
    Next
    INDEX
    Explanations

    Delta

    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
     ventilated
    -0.75
    厲害
    -0.73
    ília
    -0.73
     lining
    -0.72
     scrambling
    -0.71
    打断
    -0.71
     Retailers
    -0.71
    inä
    -0.70
    OrEqualTo
    -0.70
    тивно
    -0.70
    POSITIVE LOGITS
     Delta
    1.08
    Delta
    0.98
    rust
    0.85
     delta
    0.80
     ()=>{
    0.79
     palabra
    0.75
     erreicht
    0.74
    mainWindow
    0.74
     Свет
    0.73
    ,),
    0.73
    Activations Density 0.014%

    No Known Activations