© 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. 10-GEMMASCOPE-RES-131K
    7. 100426
    Prev
    Next
    INDEX
    Explanations

    data structures processing sequential data

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

    programming code related to data structures, arrays, and scientific computing libraries.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron spots mentions of array- or data-structure types (e.g. “array,” “DataArray,” “numpy,” “Seq,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    -1.77
     not
    -1.69
     no
    -1.59
    ne
    -1.55
     –
    -1.54
     in
    -1.45
    s
    -1.40
     back
    -1.38
     at
    -1.38
    ing
    -1.36
    POSITIVE LOGITS
    很赞
    1.70
    閿
    1.55
    ungkap
    1.51
    ❢
    1.48
    (￣
    1.45
    ключение
    1.43
     collega
    1.41
    Ukuran
    1.39
     vache
    1.39
     rê
    1.38
    Activations Density 0.038%

    No Known Activations