© 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. 66453
    Prev
    Next
    INDEX
    Explanations

    Spreadsheet applications, Thank you, Q:

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

    The neuron is specially detecting LaTeX environment delimiters (in particular the “\end” token closing an environment).

    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
    籏
    -2.39
     in
    -2.22
    もある
    -2.20
    说是
    -2.20
    e
    -2.17
    籥
    -2.02
     contoh
    -1.97
     whom
    -1.95
    ですが
    -1.92
    してみると
    -1.91
    POSITIVE LOGITS
     \
    2.41
    ↵↵
    2.38
    2
    2.25
    與
    2.11
     élas
    2.09
    1
    2.09
    讓
    2.06
    様な
    2.05
    還是
    2.00
     akzep
    1.99
    Activations Density 0.000%

    No Known Activations