© 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. 115648
    Prev
    Next
    INDEX
    Explanations

    curl function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Saltar
    -0.86
    complished
    -0.82
     упаков
    -0.77
    asiswa
    -0.76
     spazi
    -0.76
     |
    -0.75
     agregó
    -0.74
    青少年
    -0.74
    いきます
    -0.74
     _('
    -0.74
    POSITIVE LOGITS
    setopt
    1.02
     Curl
    1.00
     curl
    1.00
    curl
    0.91
    Curl
    0.86
     curling
    0.80
     curls
    0.80
     Кру
    0.75
     curled
    0.75
    目光
    0.73
    Activations Density 0.007%

    No Known Activations