© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92045
    Prev
    Next
    INDEX
    Explanations

    sale and acquisition

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

    This neuron strongly activates on very common short function words—especially high-frequency prepositions and articles like “to,” “for,” “in,” and “a.”

    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
    endaftar
    -0.84
    Ти
    -0.81
    inete
    -0.80
    Кра
    -0.78
    рыва
    -0.76
    روز
    -0.75
    ANTES
    -0.75
     ར
    -0.74
    localctx
    -0.74
     ダウン
    -0.74
    POSITIVE LOGITS
     divest
    2.41
     disposal
    2.33
     sell
    2.11
     sale
    2.09
     disposing
    2.02
     sold
    2.00
     прода
    1.98
     dives
    1.98
    出售
    1.98
     dispose
    1.95
    Activations Density 0.032%

    No Known Activations