© 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. 54357
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

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

    This neuron activates on mathematical expression tokens—particularly parentheses and numeric parts of formulas.

    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
     which
    -1.00
     другие
    -0.90
    Другие
    -0.85
     centre
    -0.85
    Geografie
    -0.83
    istorante
    -0.83
     =>'
    -0.83
     쿠
    -0.82
    一楼
    -0.82
     сельского
    -0.81
    POSITIVE LOGITS
     (
    1.19
     fiables
    1.05
     luxus
    1.03
     flesta
    1.01
    jazd
    0.97
     chô
    0.93
     sentier
    0.92
    Aiheesta
    0.92
     wó
    0.90
     effluents
    0.89
    Activations Density 0.024%

    No Known Activations