© 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. 10-GEMMASCOPE-RES-131K
    7. 100600
    Prev
    Next
    INDEX
    Explanations

    as [condition] [trend/description]

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

    The neuron selectively detects occurrences of the word “as” (including “As”) functioning as a conjunction.

    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
    ca
    -1.64
    ia
    -1.63
    ss
    -1.63
    ani
    -1.63
    ak
    -1.57
    as
    -1.55
    ar
    -1.55
    so
    -1.55
    cs
    -1.51
    一定会
    -1.51
    POSITIVE LOGITS
    çok
    1.71
     vengono
    1.67
    罍
    1.61
    Our
    1.58
     pintadas
    1.58
    correre
    1.52
     through
    1.52
    endimiento
    1.51
    ampilan
    1.49
    Through
    1.48
    Activations Density 0.047%

    No Known Activations