© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26038
    Prev
    Next
    INDEX
    Explanations

    X is Y

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

    The neuron reliably fires on occurrences of the copula “is,” picking out that linking verb wherever it appears.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     quoc
    -1.16
     печени
    -1.09
    contre
    -1.07
     bensin
    -1.05
     excesso
    -1.02
     gewi
    -1.02
     februari
    -1.01
    atherine
    -1.01
    },
    -1.01
     ligero
    -1.00
    POSITIVE LOGITS
     only
    1.47
     when
    1.20
     if
    1.20
    етка
    1.16
    meiras
    1.12
     what
    1.11
     just
    1.05
    excellents
    1.04
    HRT
    1.03
    stva
    1.01
    Activations Density 0.037%

    No Known Activations