© 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. 22-GEMMASCOPE-RES-131K
    7. 65129
    Prev
    Next
    INDEX
    Explanations

    mathematical variable y

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

    The neuron consistently activates on occurrences of the variable “y” (in equations, subscripts, and differentials).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ężczy
    -2.03
    ↵
    -1.98
    n
    -1.95
     has
    -1.94
     Some
    -1.93
    h
    -1.90
    U
    -1.84
    al
    -1.83
     burgeoning
    -1.80
     还
    -1.79
    POSITIVE LOGITS
    ｱ
    1.96
    
    1.90
    ⁛
    1.88
    ܆
    1.87
    +
    1.83
    姈
    1.83
    鷽
    1.81
     邸
    1.81
     短发
    1.79
    ₶
    1.78
    Activations Density 0.022%

    No Known Activations