© 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. 92348
    Prev
    Next
    INDEX
    Explanations

    nested lists or list structures

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

    The neuron is looking for numeric literal tokens (sequences of digits) in code and activates more strongly on larger numbers.

    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
     including
    -0.82
     and
    -0.81
     found
    -0.79
     Felsen
    -0.78
     only
    -0.77
     continued
    -0.73
    撲
    -0.72
     just
    -0.70
     Voc
    -0.69
    Demografia
    -0.69
    POSITIVE LOGITS
    nested
    1.14
    Outer
    1.05
     nested
    1.04
    Each
    1.02
    二维
    1.02
     each
    1.01
     moeder
    0.99
     outer
    0.99
     каждого
    0.95
    每一
    0.94
    Activations Density 0.028%

    No Known Activations