© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 729
    Prev
    Next
    INDEX
    Explanations

    Q: or Secession

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

    This neuron strongly activates on numeric characters (digits) in the 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_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
    0
    -0.93
    mathbf
    -0.85
     –
    -0.84
    ární
    -0.80
    火的
    -0.79
    火
    -0.79
     épices
    -0.76
    ↵↵↵
    -0.76
    and
    -0.75
     Median
    -0.74
    POSITIVE LOGITS
     your
    1.08
    Ultimately
    0.95
    Instead
    0.94
    瞼
    0.90
    Volver
    0.87
    nieder
    0.87
     działal
    0.86
    柟
    0.86
    $^\
    0.85
     ı
    0.85
    Activations Density 0.006%

    No Known Activations