© 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. 110912
    Prev
    Next
    INDEX
    Explanations

    /res segments

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

    The neuron activates on numeric literals (numbers) embedded in XML/markup attributes.

    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
    hever
    -0.77
     väga
    -0.72
    собы
    -0.70
    פרס
    -0.69
    athread
    -0.69
    ginx
    -0.68
     gérer
    -0.67
    ยา
    -0.67
    ="../../
    -0.66
     читать
    -0.66
    POSITIVE LOGITS
    teborg
    0.69
     Guth
    0.67
     Michelangelo
    0.67
     نک
    0.65
    ibm
    0.65
     тра
    0.65
     Prod
    0.64
     gången
    0.63
     called
    0.62
     maintained
    0.62
    Activations Density 0.094%

    No Known Activations