© 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. 76015
    Prev
    Next
    INDEX
    Explanations

    Mond/Mund prefixes

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

    This neuron detects occurrences of the substring “Mond” at the start of tokens.

    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
     demand
    -0.91
     demanded
    -0.83
     demands
    -0.82
    asked
    -0.79
    acquisto
    -0.78
    impresa
    -0.77
    нар
    -0.76
    checked
    -0.76
    arrivo
    -0.75
     asked
    -0.74
    POSITIVE LOGITS
    ське
    0.81
     disbursed
    0.78
     Selena
    0.77
     volunt
    0.76
     vulgaris
    0.76
     vietnam
    0.74
    ricated
    0.73
     Crucifix
    0.71
     crucifixion
    0.71
     rego
    0.69
    Activations Density 0.017%

    No Known Activations