© 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. 10-GEMMASCOPE-RES-131K
    7. 43177
    Prev
    Next
    INDEX
    Explanations

    string stream formatting and conversion

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

    The neuron activates on code tokens that contain “stream” (e.g. sstream, istream, StringStream).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -2.97
    $
    -1.67
    された
    -1.63
     sofern
    -1.63
     politischen
    -1.59
     {
    -1.56
     by
    -1.53
     erfolgreichen
    -1.52
     gemeinsamen
    -1.51
     demanding
    -1.49
    POSITIVE LOGITS
     hvem
    1.77
    iczne
    1.70
    
    1.65
     normalt
    1.63
     kollu
    1.61
     öv
    1.59
     fortsatt
    1.57
     dakika
    1.57
     ansik
    1.56
     medarbe
    1.56
    Activations Density 0.004%

    No Known Activations