© 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. 92257
    Prev
    Next
    INDEX
    Explanations

    to say

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

    The neuron strongly activates on the fixed expression “to say.”

    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
    lış
    -0.88
    לות
    -0.79
     нього
    -0.76
    большой
    -0.75
    neming
    -0.75
    lanır
    -0.75
     oluyor
    -0.75
    əri
    -0.73
    ховик
    -0.73
    ecki
    -0.73
    POSITIVE LOGITS
     say
    8.06
    say
    5.91
    Say
    5.19
     Say
    4.88
     says
    4.38
     SAY
    4.28
    SAY
    3.86
     сказать
    3.72
     saying
    3.56
    说
    3.53
    Activations Density 0.049%

    No Known Activations