© 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. 11414
    Prev
    Next
    INDEX
    Explanations

    closing punctuation before code syntax

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

    closing parentheses or brackets in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires strongly on closing square‐bracket tokens ( “]” ) in code.

    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
    딪
    -1.61
    裥
    -1.61
    楽しめる
    -1.51
    あら
    -1.45
     catég
    -1.41
    츰
    -1.37
    罍
    -1.36
     perpé
    -1.35
     khiển
    -1.34
     mentre
    -1.34
    POSITIVE LOGITS
     "
    1.45
    ↵
    1.42
     ‘
    1.38
     mostly
    1.28
     accents
    1.26
     '
    1.22
     all
    1.22
     biggest
    1.20
     more
    1.17
     respectivas
    1.16
    Activations Density 0.061%

    No Known Activations