© 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. 100343
    Prev
    Next
    INDEX
    Explanations

    power and wattage

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

    The neuron activates on numeric measurement tokens—i.e. numbers (often decimals) associated with technical specifications or quantified values.

    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
     membagikan
    -1.73
     systemu
    -1.71
    鼉
    -1.63
    if
    -1.62
     capucha
    -1.56
    ⡯
    -1.54
     pelota
    -1.52
     artikel
    -1.52
     élections
    -1.50
     твои
    -1.50
    POSITIVE LOGITS
    -
    1.73
     Unglück
    1.57
     Its
    1.44
     to
    1.42
          
    1.42
    人也
    1.42
     -
    1.40
     Therefore
    1.38
    命的
    1.34
     damal
    1.33
    Activations Density 0.037%

    No Known Activations