© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104559
    Prev
    Next
    INDEX
    Explanations

    Jamie or Going prefixes

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

    The neuron fires specifically on occurrences of the string “juju,” as in Go import paths or package names.

    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
    䜣
    -1.58
    
    -1.51
     magnific
    -1.47
    轻声
    -1.45
    が入
    -1.45
     REALLY
    -1.44
     $^{
    -1.41
    玊
    -1.41
     Infór
    -1.41
    のイメージ
    -1.40
    POSITIVE LOGITS
    There
    2.03
    there
    1.95
     or
    1.72
     two
    1.66
    the
    1.56
    just
    1.53
    These
    1.50
     raccont
    1.48
     there
    1.48
    Some
    1.47
    Activations Density 0.000%

    No Known Activations