© 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. 10-GEMMASCOPE-RES-131K
    7. 41839
    Prev
    Next
    INDEX
    Explanations

    down followed by prepositions

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

    The neuron consistently activates on the token “down.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    are
    -2.19
    when
    -1.93
    S
    -1.91
    J
    -1.90
    6
    -1.90
    1
    -1.88
    [
    -1.80
    
    -1.80
    4
    -1.77
    깐
    -1.73
    POSITIVE LOGITS
     in
    2.03
     ajud
    1.81
     With
    1.75
    ↵
    1.72
     produse
    1.65
    Semitic
    1.63
    满了
    1.62
    icação
    1.57
    焌
    1.55
     importanti
    1.54
    Activations Density 0.002%

    No Known Activations