© 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. 80732
    Prev
    Next
    INDEX
    Explanations

    foreign language characters and code snippets

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

    The neuron strongly activates on long runs of whitespace (indentation or large blank space sequences).

    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
     through
    -0.98
    AppDelegate
    -0.97
     specific
    -0.95
     only
    -0.91
     still
    -0.90
     small
    -0.87
     former
    -0.86
     by
    -0.84
     research
    -0.84
     smaller
    -0.84
    POSITIVE LOGITS
     weiteren
    1.02
    胫
    0.99
     gewissen
    0.96
    ੲ
    0.93
    Produits
    0.87
    ropractic
    0.87
     дальше
    0.87
    嘣
    0.86
     beträ
    0.85
     roxo
    0.84
    Activations Density 0.008%

    No Known Activations