© 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. 34-GEMMASCOPE-RES-131K
    7. 84064
    Prev
    Next
    INDEX
    Explanations

    quotes, brackets, braces

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

    The neuron flags content words in commented configuration‐file instructions (i.e. the explanatory text in the commented Doxygen config lines).

    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
    知り
    -0.85
    хані
    -0.74
    obus
    -0.73
    )+\
    -0.73
     whor
    -0.72
    )}{\
    -0.71
    hasPermission
    -0.71
    Ặ
    -0.70
    irat
    -0.69
    HKEY
    -0.69
    POSITIVE LOGITS
     brackets
    2.02
     {}
    1.64
     "{}
    1.62
    {}
    1.56
     '{}
    1.53
    brackets
    1.44
     braces
    1.36
    ("{}
    1.34
     enclosing
    1.32
     []
    1.31
    Activations Density 0.082%

    No Known Activations