© 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. 113068
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    This neuron activates on standalone numeric tokens (numbers) within the mathematical 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_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
    </em>
    -1.97
     that
    -1.91
     one
    -1.40
    četně
    -1.38
     mutual
    -1.35
     dinoss
    -1.35
     brilho
    -1.34
     spiele
    -1.34
    ↵↵
    -1.33
     usual
    -1.31
    POSITIVE LOGITS
     financiar
    1.63
    찮
    1.48
     ciment
    1.39
    螈
    1.39
     потрібно
    1.35
     turco
    1.33
     prevenir
    1.33
     emblema
    1.30
     monstruos
    1.30
    Nuestro
    1.28
    Activations Density 0.221%

    No Known Activations