© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6074
    Prev
    Next
    INDEX
    Explanations

    newline character

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

    The neuron activates on tokens representing line breaks or explicit break markers (e.g. “\n” or “<br>”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ite
    0.95
    us
    0.84
    os
    0.83
    ate
    0.82
    اي
    0.80
    y
    0.80
    ad
    0.77
    un
    0.77
    ي
    0.73
    tól
    0.73
    POSITIVE LOGITS
    可以
    1.01
     serez
    0.83
     deline
    0.80
     nvidia
    0.79
    んですよね
    0.79
    然后
    0.78
     вам
    0.77
    رر
    0.77
     बवाल
    0.77
    您可以
    0.77
    Activations Density 0.000%

    No Known Activations