© 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. 115795
    Prev
    Next
    INDEX
    Explanations

    electronic control of motors

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

    The neuron is triggered by technical/specification tokens—numbers, model or command codes, and other uppercase identifiers typically found in code snippets or product and protocol specifications.

    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
     Sensing
    -0.77
    bou
    -0.69
    萱
    -0.68
     Trabaj
    -0.68
    centes
    -0.67
     尔
    -0.67
     обуви
    -0.67
    scaleY
    -0.66
     シャンプー
    -0.66
    证明
    -0.66
    POSITIVE LOGITS
     servo
    0.85
     perdió
    0.83
     stepper
    0.81
     jog
    0.79
    抖
    0.79
    匕
    0.78
     motion
    0.77
     ось
    0.76
     MPG
    0.75
     fáciles
    0.75
    Activations Density 0.013%

    No Known Activations