© 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. 10-GEMMASCOPE-RES-131K
    4. 41910
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

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

    The neuron is specially tuned to spot numeric tokens (including equation numbers and numeric constants) within LaTeX/math content.

    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
    Such
    -2.00
    last
    -1.91
    getting
    -1.79
    Approximately
    -1.77
     vingt
    -1.76
    饃
    -1.76
     时尚
    -1.75
    and
    -1.75
     unbelievably
    -1.75
    return
    -1.74
    POSITIVE LOGITS
     barcos
    1.95
     animados
    1.91
     When
    1.87
    blusa
    1.84
     competitivos
    1.80
     because
    1.71
    ㈮
    1.68
     ziemlich
    1.61
    つは
    1.61
    gorro
    1.60
    Activations Density 0.023%

    No Known Activations