© 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. 91055
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and operators

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

    This neuron activates on numeric tokens (digits or numbers) within mathematical or LaTeX expressions.

    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
     from
    -1.07
     because
    -1.02
     Although
    -1.00
     There
    -0.96
    ;
    -0.95
     that
    -0.95
     their
    -0.93
     between
    -0.93
     so
    -0.89
     During
    -0.89
    POSITIVE LOGITS
     plafon
    1.05
     ULT
    1.05
    
    1.04
     PRIM
    1.02
     rivi
    1.01
     châ
    1.00
     monstre
    0.99
     entré
    0.98
     GRASS
    0.97
     Océ
    0.96
    Activations Density 0.021%

    No Known Activations