© 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. 47923
    Prev
    Next
    INDEX
    Explanations

    control of desired trajectories

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

    The neuron is highly responsive to technical, scientific prose—particularly specialized terminology and numeric or formal descriptors common in academic or engineering texts.

    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
    摂取
    -0.79
     sandals
    -0.74
     apartments
    -0.72
    maillot
    -0.72
    清洁
    -0.72
    感
    -0.71
     éditions
    -0.71
    mena
    -0.71
     Sommers
    -0.71
    بار
    -0.70
    POSITIVE LOGITS
     trajectory
    1.43
     planning
    1.34
     trajectories
    1.33
    规划
    1.03
     planners
    1.02
    trajectory
    1.02
    planning
    1.02
     path
    0.98
     trayectoria
    0.98
     trajet
    0.98
    Activations Density 0.028%

    No Known Activations