© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119373
    Prev
    Next
    INDEX
    Explanations

    New Delhi

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

    This neuron detects the capitalized word “New.”

    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
     Analyse
    -0.78
     einerseits
    -0.75
     が
    -0.73
     alugar
    -0.71
     história
    -0.70
     inspec
    -0.70
    Transmit
    -0.69
     verfügb
    -0.69
     tre
    -0.69
     до
    -0.68
    POSITIVE LOGITS
     arrivals
    0.98
     Zelanda
    0.98
     Zealand
    0.96
    JER
    0.91
     trends
    0.90
     zealand
    0.90
     Woche
    0.88
     Ambient
    0.87
     peruan
    0.86
    ording
    0.85
    Activations Density 0.034%

    No Known Activations