© 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. 71361
    Prev
    Next
    INDEX
    Explanations

    mathematical or code contexts

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

    This neuron responds to tokens that denote the start of a mathematical equation, in particular the “=” sign (often at the beginning of a line) and the numbers that follow it.

    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
    There
    -1.98
     recientemente
    -1.81
     größeren
    -1.76
     unglaub
    -1.75
     äußerst
    -1.73
    We
    -1.72
     außergewöhn
    -1.72
     fracaso
    -1.71
     außerord
    -1.70
     starken
    -1.68
    POSITIVE LOGITS
     =
    1.82
    ;
    1.66
    FundMe
    1.60
     Changer
    1.52
     DÍA
    1.50
     merk
    1.46
     paar
    1.45
    
    1.45
     lopez
    1.45
     carlo
    1.43
    Activations Density 0.020%

    No Known Activations