© 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. 84635
    Prev
    Next
    INDEX
    Explanations

    code, markup, and foreign scripts

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

    The neuron fires on long runs of leading whitespace (i.e. indentation) in code or config snippets.

    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
     those
    -1.06
    queria
    -1.01
    +#
    -0.94
     permainan
    -0.93
    embley
    -0.90
    ഉ
    -0.90
    ？』
    -0.88
    ьет
    -0.88
    cías
    -0.87
    スタム
    -0.85
    POSITIVE LOGITS
    )
    1.04
     auch
    1.00
     –
    0.93
    也要
    0.91
     привле
    0.87
     גם
    0.87
    初步
    0.86
     también
    0.84
    нциклопедия
    0.84
    te
    0.82
    Activations Density 0.000%

    No Known Activations