© 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. 47772
    Prev
    Next
    INDEX
    Explanations

    as soon as action

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

    The neuron detects the subordinating conjunction phrase “as soon as.”

    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
     също
    -1.92
     también
    -1.77
     cependant
    -1.75
     also
    -1.64
     também
    -1.63
     seulement
    -1.61
     також
    -1.59
     alſo
    -1.56
     utilisée
    -1.55
     также
    -1.48
    POSITIVE LOGITS
     from
    2.41
     their
    2.11
     two
    1.91
     three
    1.75
     it
    1.74
     or
    1.70
     both
    1.62
     theres
    1.62
     Sobald
    1.61
     one
    1.59
    Activations Density 0.029%

    No Known Activations