© 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. 103356
    Prev
    Next
    INDEX
    Explanations

    abbreviations for technical terms

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

    The neuron fires on short, all-caps letter sequences (two-letter acronyms/abbreviations).

    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
    Easier
    -0.96
     latter
    -0.96
     in
    -0.94
    Failing
    -0.93
    是我们
    -0.92
    娯
    -0.92
     papild
    -0.91
    Boletín
    -0.90
    ieR
    -0.90
     plupart
    -0.87
    POSITIVE LOGITS
    Hold
    0.94
     izquierdo
    0.93
    瘫
    0.91
     紀
    0.90
     répondre
    0.90
    这些
    0.88
     gewo
    0.88
    فصل
    0.88
    Dalam
    0.87
     chercher
    0.87
    Activations Density 0.171%

    No Known Activations