© 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. 10-GEMMASCOPE-RES-131K
    7. 9883
    Prev
    Next
    INDEX
    Explanations

    gem install

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

    The neuron is triggered by mentions of software packages or modules (e.g. “package,” “packages,” “gem,” “library,” “bundler,” etc.) in dependency/import contexts.

    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
     for
    -1.59
     all
    -1.57
    "
    -1.52
     had
    -1.50
     an
    -1.45
     through
    -1.45
     made
    -1.41
    。”
    -1.40
     unparalleled
    -1.39
     because
    -1.37
    POSITIVE LOGITS
     EIGHT
    1.76
     FOUR
    1.70
     FIVE
    1.68
     overal
    1.64
    犼
    1.62
     SEVEN
    1.60
     ρ
    1.59
     getNome
    1.55
     contener
    1.55
                               
    1.55
    Activations Density 0.086%

    No Known Activations