© 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. 66098
    Prev
    Next
    INDEX
    Explanations

    spreading the word

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

    The neuron is highly tuned to the phrase “spread the word.”

    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
     Braxton
    -0.88
    apples
    -0.85
     فلزی
    -0.77
     blijven
    -0.74
     Маке
    -0.74
     speelt
    -0.74
    Nieuwe
    -0.73
    Isaiah
    -0.72
     plantillas
    -0.71
    čné
    -0.69
    POSITIVE LOGITS
     word
    7.22
    word
    5.25
    Word
    4.81
     Word
    4.69
    WORD
    4.28
     palabra
    4.22
     WORD
    4.06
     слово
    4.03
     palavra
    3.88
     words
    3.45
    Activations Density 0.033%

    No Known Activations