© 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. 13734
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

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

    The neuron specifically detects LaTeX display‐math regions (e.g. “$$ … $$” and related math‐mode tokens).

    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
    というわけで
    -1.05
     doká
    -1.04
     impecable
    -1.04
     then
    -0.98
     and
    -0.97
     pernic
    -0.96
    　　《
    -0.95
    Penjelasan
    -0.94
    Transcripción
    -0.94
    もちろん
    -0.94
    POSITIVE LOGITS
    𝟑
    1.06
     gutem
    1.00
     welcher
    0.99
    ()}>
    0.98
     seinem
    0.98
     zwi
    0.97
     feiner
    0.97
     natür
    0.97
     gewe
    0.96
    Terminate
    0.96
    Activations Density 0.040%

    No Known Activations