© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95844
    Prev
    Next
    INDEX
    Explanations

    solving mathematical problems

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

    The neuron strongly activates on LaTeX math‐mode constructs (especially environment beginnings like “\begin{cases},” math delimiters, and related symbols).

    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
     incapa
    -0.99
     Livro
    -0.96
    Einen
    -0.95
     constitue
    -0.93
     multicolore
    -0.93
    bouncycastle
    -0.91
    polated
    -0.90
     manteiga
    -0.88
     empat
    -0.88
     aplicaciones
    -0.88
    POSITIVE LOGITS
     zacht
    0.91
    NewUrl
    0.91
    ៹
    0.90
     volledige
    0.88
    愿
    0.88
    騁
    0.86
     mantenga
    0.85
    ObjectID
    0.85
     until
    0.85
    老头
    0.84
    Activations Density 0.019%

    No Known Activations