© 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. 69258
    Prev
    Next
    INDEX
    Explanations

    Cyclic stretch

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

    backslash characters in programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on backslash escape sequences (i.e. “\\” used for escaping in strings or regex).

    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
    罍
    -1.89
    猹
    -1.86
    癀
    -1.78
     ſont
    -1.76
    の情報
    -1.76
     frança
    -1.72
    \&
    -1.69
     alimente
    -1.68
    都沒有
    -1.65
     merve
    -1.62
    POSITIVE LOGITS
    “
    2.33
    breviations
    2.14
     machten
    1.95
     dritten
    1.92
    You
    1.88
     harten
    1.85
     neighborhoods
    1.84
    ₄
    1.82
     mußten
    1.80
    StoryboardSegue
    1.73
    Activations Density 0.012%

    No Known Activations