© 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. 81498
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns

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

    The neuron strongly activates on capitalized tokens—especially proper names or named-entity words.

    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
    不同
    -0.76
     cavern
    -0.76
     particolarmente
    -0.75
     $+\
    -0.73
    Salir
    -0.73
     navel
    -0.73
    ができます
    -0.73
    っぽい
    -0.72
    ticularly
    -0.71
    urgi
    -0.71
    POSITIVE LOGITS
     المهم
    0.85
     légitime
    0.83
     lull
    0.81
     deduction
    0.79
     devait
    0.79
     impreso
    0.78
    鱷
    0.78
     мысли
    0.77
    »»
    0.77
    挫
    0.77
    Activations Density 0.303%

    No Known Activations