© 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. 3673
    Prev
    Next
    INDEX
    Explanations

    index notation like $\sum_i$

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

    The neuron fires on the subscripted index “i” in mathematical formulas, detecting occurrences of the variable i used as an index in equations.

    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
    {
    -2.98
    6
    -2.91
     {
    -2.89
     behulp
    -2.88
    $
    -2.78
    Ꭳ
    -2.72
    鱚
    -2.55
    8
    -2.48
    9
    -2.44
     faca
    -2.42
    POSITIVE LOGITS
    趼
    2.47
    眥
    2.38
    lusconi
    2.38
    。
    2.28
    Elaboración
    2.27
     diseñ
    2.23
     éstas
    2.17
     Электро
    2.16
     Германия
    2.16
    同上
    2.16
    Activations Density 0.066%

    No Known Activations