© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59245
    Prev
    Next
    INDEX
    Explanations

    newline character

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

    The neuron fires on newline characters (line‐break tokens) in the text.

    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
    鳎
    -2.06
     eventuali
    -2.05
     damaligen
    -2.03
     tomando
    -1.99
    
    -1.96
     trám
    -1.96
    vège
    -1.95
    
    -1.93
    鮠
    -1.84
    胀
    -1.84
    POSITIVE LOGITS
    In
    2.16
    We
    2.14
     .
    1.99
    是
    1.92
    !
    1.92
     possib
    1.75
    жа
    1.74
    *
    1.72
     リ
    1.70
    等到
    1.68
    Activations Density 0.003%

    No Known Activations