© 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. 118101
    Prev
    Next
    INDEX
    Explanations

    url encoding and decoding

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

    The neuron responds to numeric literals—tokens consisting of digit sequences (e.g. “426”, “2464”, “1080”).

    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
     andere
    -0.79
    url
    -0.77
    Eu
    -0.76
     nélk
    -0.76
    után
    -0.75
    NNY
    -0.74
    atorio
    -0.73
     تحتاج
    -0.73
    鍏
    -0.73
    ρου
    -0.72
    POSITIVE LOGITS
     encode
    2.69
    encode
    2.56
    decode
    2.25
     decode
    2.20
    Encode
    1.77
     Encode
    1.67
     escape
    1.65
    escape
    1.62
     Decode
    1.60
     encodes
    1.59
    Activations Density 0.016%

    No Known Activations