© 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. 34-GEMMASCOPE-RES-131K
    7. 84943
    Prev
    Next
    INDEX
    Explanations

    equation numbering

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

    The neuron strongly activates on numeric tokens (e.g. version numbers, dimensions, package option numbers) in the LaTeX source, i.e. it detects digits or numeric values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    γγ
    -0.85
    
    -0.82
    фен
    -0.82
    ιδ
    -0.77
     norske
    -0.77
     når
    -0.73
    "،
    -0.73
     grafica
    -0.73
    、「
    -0.71
     arreg
    -0.71
    POSITIVE LOGITS
     equations
    1.47
     equation
    1.44
     numbered
    1.09
     numbering
    1.09
    equation
    1.02
     Equation
    0.99
    Equations
    0.98
     Eqs
    0.95
     Equations
    0.93
    numbered
    0.89
    Activations Density 0.009%

    No Known Activations