© 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. 33212
    Prev
    Next
    INDEX
    Explanations

    fault and transient stability

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

    The neuron strongly fires on specialized power‐systems engineering jargon—terms like “dynamic,” “transient,” “stability,” “load,” and “power system.”

    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
    了的
    -0.81
    泞
    -0.79
    CTION
    -0.76
     Eich
    -0.74
    orku
    -0.72
    ɨ
    -0.72
     Clive
    -0.71
     silla
    -0.71
    そんな
    -0.69
    vermectin
    -0.69
    POSITIVE LOGITS
     fault
    0.89
    fault
    0.84
     transient
    0.81
     initiation
    0.77
    பா
    0.76
     short
    0.75
    Transient
    0.75
     clearing
    0.74
     transients
    0.73
     contribution
    0.72
    Activations Density 0.014%

    No Known Activations