© 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. 25608
    Prev
    Next
    INDEX
    Explanations

    para prefix words

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

    The neuron activates on occurrences of the letter sequence “para” within longer words.

    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
     previously
    -0.87
    iterraneo
    -0.81
     również
    -0.79
     hitherto
    -0.79
     jahr
    -0.78
    DUE
    -0.77
     terão
    -0.77
     freshly
    -0.75
     allocator
    -0.75
    Phones
    -0.74
    POSITIVE LOGITS
     Para
    1.25
     PARA
    1.20
    Para
    1.19
     para
    1.18
    para
    1.09
    digm
    1.06
     Пара
    1.01
    パラ
    0.99
    Пара
    0.96
    paran
    0.91
    Activations Density 0.026%

    No Known Activations