© 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. 75935
    Prev
    Next
    INDEX
    Explanations

    names starting with Mack

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

    The neuron consistently activates on the character sequence “Mack,” i.e. names or words containing “Mack.”

    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
     Generalized
    -0.75
    놀
    -0.72
     良
    -0.70
    地元
    -0.70
     additional
    -0.69
     تهیه
    -0.69
    adren
    -0.68
     работой
    -0.67
    étaire
    -0.66
     confusing
    -0.66
    POSITIVE LOGITS
    ensen
    0.93
     Trucks
    0.93
    ӵ
    0.85
     truck
    0.85
     whiteboard
    0.84
     TRUCK
    0.84
     Unclassified
    0.83
     chargement
    0.81
    esar
    0.79
     Truck
    0.79
    Activations Density 0.017%

    No Known Activations