© 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. 22-GEMMASCOPE-RES-131K
    7. 95627
    Prev
    Next
    INDEX
    Explanations

    System namespace imports

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

    The neuron fires on occurrences of the identifier “System,” e.g. in using/import directives referencing the System namespace.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     alimentazione
    -1.09
    служба
    -1.08
     cương
    -1.04
    .}~\
    -1.02
    뉜
    -1.02
     Riproduzione
    -0.99
    娼
    -0.97
    terday
    -0.95
     caratteri
    -0.95
    ilée
    -0.95
    POSITIVE LOGITS
    re
    1.09
    0.99
    u
    0.98
    ist
    0.98
    骼
    0.97
    IN
    0.96
     dám
    0.95
     \
    0.95
    </h3>
    0.93
    噉
    0.93
    Activations Density 0.000%
    No Known Activations