© 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. 34-GEMMASCOPE-RES-131K
    7. 79139
    Prev
    Next
    INDEX
    Explanations

    speed and fast movement

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

    The neuron is strongly activated by common short function words (articles and prepositions) such as “in,” “the,” “a,” and “of.”

    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
    Slowly
    -0.95
     wandered
    -0.91
    walking
    -0.88
     walks
    -0.84
    baijan
    -0.82
     walk
    -0.82
    walks
    -0.82
    walk
    -0.82
     Slowly
    -0.82
    Walking
    -0.81
    POSITIVE LOGITS
     speed
    3.23
     fast
    3.03
     faster
    3.02
     fastest
    2.75
     speeds
    2.66
     speedy
    2.66
     speeding
    2.66
    speed
    2.61
    Speed
    2.48
    fast
    2.41
    Activations Density 0.070%

    No Known Activations