© 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. 34-GEMMASCOPE-RES-131K
    7. 47663
    Prev
    Next
    INDEX
    Explanations

    Date and `int` following text

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

    The neuron strongly activates on long runs of whitespace/indentation characters.

    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
     page
    -2.11
    分页
    -1.96
     PAGE
    -1.95
     pages
    -1.88
     Page
    -1.79
     página
    -1.73
     paging
    -1.73
     getPage
    -1.73
    page
    -1.69
    PAGE
    -1.69
    POSITIVE LOGITS
    par
    0.80
     cant
    0.74
     par
    0.72
     criptomonedas
    0.71
     love
    0.71
    ActionBar
    0.70
     whispered
    0.70
    PAR
    0.69
     PAR
    0.69
    Sorting
    0.69
    Activations Density 0.023%

    No Known Activations