© 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. 34-GEMMASCOPE-RES-131K
    7. 84022
    Prev
    Next
    INDEX
    Explanations

    sliding window functions

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

    The neuron detects references to sliding‐window or running/moving‐window computations (e.g. running sum, moving average, window).

    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
     բ
    -0.91
    Dougall
    -0.73
    UNIS
    -0.73
    Capa
    -0.70
    unton
    -0.69
    ੁ
    -0.68
     Bower
    -0.68
     taco
    -0.68
     Rondo
    -0.68
    upsi
    -0.68
    POSITIVE LOGITS
     sliding
    3.08
     window
    3.05
     Sliding
    2.66
    window
    2.55
    sliding
    2.53
    Sliding
    2.52
     windows
    2.52
     Window
    2.34
     rolling
    2.31
    窗口
    2.20
    Activations Density 0.048%

    No Known Activations