© 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. 47947
    Prev
    Next
    INDEX
    Explanations

    dividing or splitting

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

    The neuron is sensitive to language about partitioning or dividing things into parts (e.g. “divides,” “splitting,” “dividing,” “categories”).

    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
     only
    -1.59
     more
    -1.52
     change
    -1.48
     when
    -1.48
     without
    -1.43
     changes
    -1.43
     see
    -1.41
     even
    -1.33
    iddhar
    -1.27
     đãi
    -1.24
    POSITIVE LOGITS
    became
    1.69
    decided
    1.57
    continues
    1.51
    mostly
    1.49
    particularly
    1.41
    primarily
    1.40
    becomes
    1.39
    often
    1.39
    obviously
    1.39
    certainly
    1.38
    Activations Density 0.083%

    No Known Activations