© 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. 2378
    Prev
    Next
    INDEX
    Explanations

    describing essential components

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

    The neuron consistently fires on formal, domain‐specific content words (e.g. “tumor,” “urbanization,” “development,” “digestive,” “viable”) typical of academic or technical writing.

    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
     alltså
    -0.90
    Всё
    -0.88
    Relevant
    -0.87
     universelle
    -0.86
     florales
    -0.85
     parche
    -0.84
     robuste
    -0.84
     curé
    -0.84
     europé
    -0.83
    內容簡介
    -0.82
    POSITIVE LOGITS
    之一
    0.94
     milestone
    0.91
     a
    0.84
     felicità
    0.81
     nosso
    0.81
     بار
    0.81
     depois
    0.81
     deberían
    0.80
     another
    0.79
     tärke
    0.79
    Activations Density 0.035%

    No Known Activations