© 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. 12722
    Prev
    Next
    INDEX
    Explanations

    testing codes and frameworks

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

    This neuron fires on occurrences of the substring “test” (e.g. in identifiers, package or import names, file paths, or comments).

    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
     แต่
    -1.86
     empez
    -1.78
     pouze
    -1.76
    
    -1.71
    噲
    -1.71
    ▤
    -1.70
     poursuivre
    -1.66
     téc
    -1.66
     佐藤
    -1.66
    MSc
    -1.65
    POSITIVE LOGITS
    al
    2.80
    ar
    2.53
    an
    2.50
    re
    2.48
    in
    2.31
    ll
    2.23
     various
    2.20
    ri
    2.05
    各种
    2.02
    These
    1.95
    Activations Density 0.004%

    No Known Activations