© 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. 10-GEMMASCOPE-RES-131K
    7. 131010
    Prev
    Next
    INDEX
    Explanations

    Youth unemployment

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

    The neuron is a detector for line‐break (newline) escape tokens (“\n”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     only
    -2.08
     continuously
    -1.98
     every
    -1.96
     unrelenting
    -1.92
     expertly
    -1.87
     meticulously
    -1.83
     exquisitely
    -1.83
     superbly
    -1.81
     seemingly
    -1.80
     although
    -1.78
    POSITIVE LOGITS
     "'
    1.88
     VERY
    1.83
    feliz
    1.82
     '"
    1.77
    
    1.74
    ﮧ
    1.73
     новая
    1.71
    really
    1.71
     créer
    1.70
     ation
    1.68
    Activations Density 0.002%

    No Known Activations