© 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. 75491
    Prev
    Next
    INDEX
    Explanations

    code formatting and punctuation

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

    The neuron strongly activates on bare newline or other control‐whitespace tokens (e.g. blank lines or carriage‐returns).

    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
     racines
    -0.91
     مجتمع
    -0.83
    远远
    -0.82
    includes
    -0.81
     verwijderen
    -0.80
     jovens
    -0.80
     dreary
    -0.78
    teine
    -0.78
    εται
    -0.78
     vijf
    -0.78
    POSITIVE LOGITS
     through
    1.02
     there
    0.88
     because
    0.87
     first
    0.85
    صفات
    0.81
    iodía
    0.81
     at
    0.80
     most
    0.78
     within
    0.77
     every
    0.74
    Activations Density 0.018%

    No Known Activations