© 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. 42545
    Prev
    Next
    INDEX
    Explanations

    code snippets and keywords

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

    The neuron fires on runs of leading whitespace (indentation) 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
     destacados
    -1.98
    ("
    -1.91
    걍
    -1.87
     pourrait
    -1.80
     мои
    -1.78
     tht
    -1.77
    ilización
    -1.77
     decorados
    -1.75
     Strukturen
    -1.75
    âmica
    -1.75
    POSITIVE LOGITS
     to
    2.23
     when
    2.11
     at
    2.09
     because
    2.09
     even
    1.97
     if
    1.97
     can
    1.96
     until
    1.84
     during
    1.83
    ’
    1.81
    Activations Density 0.029%

    No Known Activations