© 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. 128874
    Prev
    Next
    INDEX
    Explanations

    This neuron detects Big-O complexity notation (expressions of time/space complexity like O(n), O(n + m), etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Victoria And Backpack

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    rucks
    -1.46
     bună
    -1.11
    Btu
    -1.09
     mít
    -1.09
    atividade
    -1.08
     instalada
    -1.06
     protegida
    -1.06
    grafica
    -1.06
     Ně
    -1.05
     Popis
    -1.05
    POSITIVE LOGITS
    If
    1.18
     if
    1.10
     puisque
    1.09
     used
    0.97
    🧆
    0.95
    講師
    0.94
    Maße
    0.94
    During
    0.94
    AMIENTO
    0.93
    adí
    0.93
    Activations Density 0.005%

    No Known Activations