© 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. 109314
    Prev
    Next
    INDEX
    Explanations

    hy and following syllables

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

    This neuron activates on tokens containing the letter sequence “Hy,” i.e. words beginning with “Hy.”

    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
     actually
    -0.86
    çado
    -0.85
     normally
    -0.85
    loride
    -0.82
     either
    -0.79
     Sust
    -0.75
     beobach
    -0.74
     Überras
    -0.74
    声優
    -0.73
     また
    -0.72
    POSITIVE LOGITS
     Hy
    1.34
    Hy
    1.28
     hy
    1.09
    拾
    1.02
     HY
    0.89
     Vereinigten
    0.84
     ги
    0.82
    hy
    0.81
     Flanagan
    0.81
     geval
    0.81
    Activations Density 0.042%

    No Known Activations