© 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. 83148
    Prev
    Next
    INDEX
    Explanations

    opening curly brace `{`

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

    The neuron mainly responds to numeric literals (integer constants) in 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
     especially
    -1.07
     soprattutto
    -1.01
     principalmente
    -0.97
     особенно
    -0.93
    unos
    -0.84
    JsonNode
    -0.81
     mostly
    -0.80
    especially
    -0.79
    inergic
    -0.77
     mainly
    -0.77
    POSITIVE LOGITS
     {
    1.44
     {
    1.27
    {
    1.15
    ówczas
    1.06
     $\{\
    0.98
     $\{
    0.96
     thì
    0.94
    obald
    0.93
     then
    0.91
    öpfe
    0.88
    Activations Density 0.008%

    No Known Activations