© 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. 34-GEMMASCOPE-RES-131K
    7. 78009
    Prev
    Next
    INDEX
    Explanations

    power system components

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

    The neuron strongly activates on technical, domain‐specific vocabulary—especially power‐systems and engineering terms in an academic abstract.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     MainAxisSize
    -0.87
     thermometer
    -0.86
    licone
    -0.86
     assistir
    -0.85
    WERS
    -0.84
    ΡΟ
    -0.82
     strumento
    -0.82
    abled
    -0.82
    
    -0.81
    fits
    -0.79
    POSITIVE LOGITS
     voltage
    1.55
     IEEE
    1.45
    IEEE
    1.41
     load
    1.29
    voltage
    1.17
     tripping
    1.13
     buses
    1.13
     loads
    1.09
     Voltage
    1.08
     bus
    1.07
    Activations Density 0.082%

    No Known Activations