© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71805
    Prev
    Next
    INDEX
    Explanations

    text wrapping and line breaks

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

    This neuron detects occurrences of the CSS “white-space: pre” declaration.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    
    -1.29
     ſever
    -1.21
     différents
    -1.18
     ij
    -1.15
    
    -1.13
     erhi
    -1.12
     galinha
    -1.09
     vazio
    -1.09
    きち
    -1.08
    mbgg
    -1.06
    POSITIVE LOGITS
     so
    1.78
     allows
    1.47
     through
    1.45
     allow
    1.40
     allowing
    1.39
     When
    1.33
     ....
    1.31
     nestled
    1.30
     Trying
    1.28
    .......
    1.27
    Activations Density 0.008%

    No Known Activations