© 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. 22-GEMMASCOPE-RES-131K
    7. 36310
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting

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

    The neuron detects markdown emphasis markers (i.e. the `*` and `_` tokens used for italic/bold formatting).

    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
    t
    -1.89
    '
    -1.84
     enten
    -1.75
    "
    -1.64
    ,
    -1.61
    us
    -1.56
     eenig
    -1.53
    页面存档备份
    -1.50
     They
    -1.50
     quels
    -1.47
    POSITIVE LOGITS
    ↵
    1.98
    ’.
    1.63
    事態
    1.52
    ixante
    1.50
     münchen
    1.50
    ’,
    1.39
    savevideo
    1.38
     makanan
    1.38
     ventanas
    1.38
    detroit
    1.38
    Activations Density 0.084%

    No Known Activations