© 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. 10-GEMMASCOPE-RES-131K
    7. 42511
    Prev
    Next
    INDEX
    Explanations

    electrical currents

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

    The neuron is strongly triggered by the word “currents” (in any context, e.g. ocean currents or electrical/ionic currents).

    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
    луйста
    -2.69
     花卉
    -2.61
     剤
    -2.58
    er
    -2.52
    ৯
    -2.50
    ſam
    -2.48
    饪
    -2.45
     như
    -2.44
    u
    -2.44
    と思っています
    -2.42
    POSITIVE LOGITS
     
    3.83
    '
    3.73
      
    3.50
     currents
    2.61
    </strong>
    2.58
    "
    2.48
    ↵
    2.33
    ↵↵
    2.25
    -
    2.23
    很不
    2.22
    Activations Density 0.002%

    No Known Activations