© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116303
    Prev
    Next
    INDEX
    Explanations

    getting lists of items

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

    The neuron flags programming-language code tokens—especially generic type names and related syntax (e.g. List, get, “[]”, angle-bracketed types).

    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
     one
    -0.98
    :
    -0.93
    Stocks
    -0.93
    的那
    -0.91
     Limits
    -0.89
     isn
    -0.89
     pecans
    -0.88
     isComment
    -0.87
     on
    -0.86
     contextLoads
    -0.86
    POSITIVE LOGITS
    所有的
    1.48
     semua
    1.45
     wszystkie
    1.41
     všechny
    1.41
     всички
    1.33
     all
    1.31
     wszystkich
    1.29
    的所有
    1.27
    possibly
    1.25
    additional
    1.24
    Activations Density 0.054%

    No Known Activations