© 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. 10-GEMMASCOPE-RES-131K
    7. 72825
    Prev
    Next
    INDEX
    Explanations

    summation indices

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

    The neuron specializes in spotting LaTeX‐style summation expressions (i.e. occurrences of “sum” with subscripts and superscripts).

    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
    但她
    -1.90
    -
    -1.87
    但他
    -1.87
     brist
    -1.78
    把她
    -1.72
     largely
    -1.65
     jn
    -1.63
     ridd
    -1.61
     trum
    -1.61
     entièrement
    -1.59
    POSITIVE LOGITS
     that
    2.16
    佧
    2.06
    琁
    1.88
    珦
    1.86
    1.83
     with
    1.80
    
    1.80
     it
    1.79
    偁
    1.78
    卨
    1.78
    Activations Density 0.005%

    No Known Activations