© 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. 82314
    Prev
    Next
    INDEX
    Explanations

    auto repair and maintenance

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

    The neuron is looking for numeric tokens (digits or numbers) representing quantities, measures, or counts in the text.

    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
     Arce
    -0.79
    Mj
    -0.75
     ASL
    -0.72
    oblotting
    -0.72
    ftest
    -0.71
     QQ
    -0.71
     рестай
    -0.71
    webdriver
    -0.70
    事業
    -0.70
     textStatus
    -0.69
    POSITIVE LOGITS
     oil
    1.70
     Oil
    1.60
     tires
    1.42
    Oil
    1.34
    oil
    1.30
     fluids
    1.28
     tire
    1.27
     routine
    1.26
    オイル
    1.25
     brakes
    1.17
    Activations Density 0.016%

    No Known Activations