© 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. 19463
    Prev
    Next
    INDEX
    Explanations

    beginning of processes

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

    The neuron strongly activates on the copular verb “is,” especially when it introduces definitional or role‐describing statements.

    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
     alho
    -2.19
     nader
    -1.64
     koper
    -1.63
     maniere
    -1.63
     nabo
    -1.59
     indien
    -1.56
     melk
    -1.54
    ํ
    -1.54
     poches
    -1.54
     dage
    -1.53
    POSITIVE LOGITS
     more
    2.16
    ;
    1.91
    ),
    1.81
     its
    1.77
     over
    1.72
     an
    1.66
     various
    1.65
     increased
    1.61
     и
    1.60
     numerous
    1.59
    Activations Density 0.180%

    No Known Activations