© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66813
    Prev
    Next
    INDEX
    Explanations

    calculus integrals or mathematical formulas

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

    The neuron fires on tokens representing integration differential operators (e.g. “dx,” “dy,” “dz,” “dA”).

    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
     on
    -1.03
    руб
    -1.02
     Fotografie
    -0.95
    llung
    -0.91
     кӀош
    -0.90
    òn
    -0.90
    EXECUTIVE
    -0.89
     تكون
    -0.89
    (\%)
    -0.89
     to
    -0.88
    POSITIVE LOGITS
     actifs
    1.13
     ťaž
    1.02
    Première
    0.99
     متعلقه
    0.98
     zuge
    0.97
     hábit
    0.97
    unico
    0.96
    tesy
    0.95
     hígado
    0.94
    Numéro
    0.92
    Activations Density 0.003%

    No Known Activations