© 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. 86985
    Prev
    Next
    INDEX
    Explanations

    Javier Velázquez

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

    The neuron is detecting code‐style structural tokens—runs of punctuation, digits, underscores, and indentation whitespace.

    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
     ayı
    -0.96
    JAMIN
    -0.87
     apareció
    -0.78
    ётся
    -0.77
     Appell
    -0.76
     hicimos
    -0.76
     hadir
    -0.75
    competi
    -0.75
     требует
    -0.74
    typeout
    -0.73
    POSITIVE LOGITS
     Sequential
    0.96
    Sequential
    0.93
     ques
    0.86
    Allemagne
    0.84
     conversación
    0.84
     conversation
    0.84
     ходе
    0.83
     responses
    0.82
    чков
    0.80
     answers
    0.79
    Activations Density 0.005%

    No Known Activations