© 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. 69841
    Prev
    Next
    INDEX
    Explanations

    differential followed by effect descriptor

    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
     vierte
    -1.05
    鬭
    -0.94
     erhi
    -0.93
     treff
    -0.92
    🆗
    -0.90
     dritte
    -0.89
     bergen
    -0.86
    Onde
    -0.85
    archiwizowane
    -0.84
    腚
    -0.84
    POSITIVE LOGITS
     Differential
    1.28
    differential
    1.19
    Differential
    1.11
     calculus
    1.02
     Privacy
    1.00
     differential
    0.93
     equations
    0.92
    openzeppelin
    0.90
     games
    0.88
    墅
    0.88
    Activations Density 0.026%

    No Known Activations