© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1656
    Prev
    Next
    INDEX
    Explanations

    `def`, `Q:`, `Ty`, `K`

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

    The neuron detects programming or markup tokens—things like the Python keyword “def,” XML/HTML angle brackets “<,” and similar code-style elements.

    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
    お楽しみに
    -0.82
     shone
    -0.78
     Kette
    -0.77
     within
    -0.75
     wró
    -0.75
    為主
    -0.74
    兩種
    -0.71
    šanās
    -0.70
    ısında
    -0.70
     solltest
    -0.68
    POSITIVE LOGITS
     finale
    0.85
    iert
    0.82
     real
    0.80
     бюро
    0.80
    周辺
    0.78
    чков
    0.77
    States
    0.77
    Hier
    0.76
     Therese
    0.76
    Funding
    0.75
    Activations Density 0.000%

    No Known Activations