© 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. 109378
    Prev
    Next
    INDEX
    Explanations

    actions followed by against

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

    This neuron fires strongly on the preposition “against” and the key noun that follows it (e.g. “race against time,” “fight against extremism,” “defense against infection,” “charges lodged against”).

    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
     nhãn
    -0.82
    Исто
    -0.81
    をお願い
    -0.81
    lisle
    -0.80
    貍
    -0.79
    льевич
    -0.79
     plonge
    -0.79
    orced
    -0.79
    ėjo
    -0.78
    кумулятор
    -0.78
    POSITIVE LOGITS
     against
    10.81
    against
    6.97
    Against
    6.75
     Against
    6.28
     против
    5.53
     AGAINST
    4.94
     gegen
    4.88
    foreach
    4.47
     tegen
    4.19
     contre
    3.48
    Activations Density 0.581%

    No Known Activations