© 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. 83067
    Prev
    Next
    INDEX
    Explanations

    robotics and software

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

    This neuron strongly fires on non‐alphanumeric formatting tokens (e.g. backticks, tildes, asterisks, parentheses, and other punctuation marks) commonly used in code or markdown.

    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
    ってみて
    -0.74
     Jahr
    -0.73
    провод
    -0.70
     business
    -0.69
     Exacts
    -0.68
     concurso
    -0.67
     obč
    -0.67
     дорога
    -0.67
     Reise
    -0.67
    hender
    -0.66
    POSITIVE LOGITS
    ROS
    1.59
     ROS
    1.57
     robot
    1.56
     ros
    1.45
     gazebo
    1.44
     Gaze
    1.41
     rospy
    1.38
    rospy
    1.31
     Robotics
    1.30
     robotics
    1.29
    Activations Density 0.051%

    No Known Activations