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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128197
    Prev
    Next
    INDEX
    Explanations

    GPU computing

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on mentions of “GPU” or its spelled‐out form “graphics processing unit.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Then
    -2.75
    
    -2.59
    
    -2.55
     스타일
    -2.50
    凊
    -2.50
    at
    -2.48
    🧌
    -2.45
     essi
    -2.45
    ro
    -2.42
    salario
    -2.39
    POSITIVE LOGITS
    できれば
    2.23
     feiert
    2.17
    hilterra
    2.08
     drücken
    2.06
    arraycopy
    2.05
     отверсти
    2.03
     искать
    1.98
    рису
    1.95
     المهم
    1.94
     valgt
    1.91
    Activations Density 0.003%

    No Known Activations