© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63424
    Prev
    Next
    INDEX
    Explanations

    #!/usr

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

    The neuron strongly activates on the subword pieces spelling out the scientific name “Physcomitrella patens.”

    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
     TSC
    -0.76
    ַּ
    -0.72
     stucco
    -0.69
    icios
    -0.68
     requisition
    -0.68
     Veneto
    -0.67
    TSC
    -0.67
     때
    -0.67
     ово
    -0.66
    Js
    -0.66
    POSITIVE LOGITS
     proton
    0.98
    蒴
    0.92
    proton
    0.86
    Proton
    0.84
    forschung
    0.78
     Proton
    0.77
    liputi
    0.75
     Gemma
    0.75
    孔子
    0.74
     меся
    0.74
    Activations Density 0.023%

    No Known Activations