© 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. 127691
    Prev
    Next
    INDEX
    Explanations

    spark plug ignition combustion engines

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

    The neuron detects technical terms related to internal-combustion engine components, especially ignition system parts like spark plugs, combustion chamber, valves, and related terminology.

    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
     primeira
    -1.43
     stroom
    -1.41
    龊
    -1.31
     nein
    -1.28
     وط
    -1.23
     webu
    -1.19
     wonderful
    -1.16
     サイズ
    -1.16
     dangerously
    -1.16
     می‌توانید
    -1.14
    POSITIVE LOGITS
     tertentu
    1.34
    鄖
    1.16
    виси
    1.16
     arroyo
    1.13
     automne
    1.13
    among
    1.11
    ویه
    1.11
     Certaines
    1.11
     сказали
    1.10
    льники
    1.09
    Activations Density 0.031%

    No Known Activations