© 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. 22-GEMMASCOPE-RES-131K
    7. 68029
    Prev
    Next
    INDEX
    Explanations

    code and text snippets

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

    The neuron is triggered by code‐template delimiters and punctuation (e.g. “<?”, “?>”, “{%”, “%}”, “{{”, “}}”, quotes, parentheses, etc.), i.e. syntax markers used in embedding or templating languages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     かな
    -1.02
     creazione
    -1.01
    ịa
    -0.99
     любых
    -0.97
     alcune
    -0.96
     ابت
    -0.95
     tanong
    -0.94
     říká
    -0.94
     desagrad
    -0.94
    对
    -0.92
    POSITIVE LOGITS
    –
    0.96
     психо
    0.93
     scène
    0.91
    |:
    0.91
    となりました
    0.91
     تری
    0.90
    umento
    0.90
     or
    0.88
    TRAIL
    0.87
     bender
    0.87
    Activations Density 0.002%

    No Known Activations