© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1834
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and objects

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

    This neuron fires on TeX‐style mathematical tokens—especially numbers, variables, and operators inside dollar‐delimited math.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    MIR
    -0.90
     Tinker
    -0.85
    ῥ
    -0.85
    IR
    -0.82
     creating
    -0.79
    つの
    -0.78
    Ad
    -0.77
    open
    -0.75
    ης
    -0.75
    MULT
    -0.75
    POSITIVE LOGITS
    Ayrıca
    0.88
     STRUCTURE
    0.87
    ར་བ
    0.84
     équipement
    0.84
    Cevap
    0.83
    itatem
    0.82
     equipped
    0.82
     PUSTAKA
    0.81
    palabras
    0.80
    ディガン
    0.79
    Activations Density 0.048%

    No Known Activations