© 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. 12718
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with x

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

    This neuron specializes in detecting the variable “x” together with its subscript or indexed form in mathematical notation.

    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
    味わ
    -1.43
    非常に
    -1.41
    インチ
    -1.38
    >
    -1.36
     Imágenes
    -1.35
     Examples
    -1.34
    НОЕ
    -1.32
    不会
    -1.30
     felpa
    -1.29
     recensione
    -1.29
    POSITIVE LOGITS
     their
    1.48
    蟄
    1.45
    拙
    1.41
    訛
    1.41
     byproduct
    1.35
    蹉
    1.35
     versatile
    1.34
    凝土
    1.34
     preciosas
    1.30
     versátil
    1.30
    Activations Density 0.108%

    No Known Activations