© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21095
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations and problems

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

    The neuron specifically fires on occurrences of the word “arithmetic.”

    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
    ي
    -3.41
    \
    -3.39
    i
    -3.33
    2
    -2.78
    —
    -2.61
    고
    -2.45
    י
    -2.39
    在我
    -2.36
    "=>$
    -2.33
    5
    -2.31
    POSITIVE LOGITS
    .
    2.59
     acrí
    2.45
     Opiniones
    2.42
    
    2.39
     Condiciones
    2.39
    ”,
    2.34
     беже
    2.31
    beim
    2.30
     reporta
    2.27
     fant
    2.25
    Activations Density 0.010%

    No Known Activations