© 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. 8849
    Prev
    Next
    INDEX
    Explanations

    [subject] is [description]

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

    The neuron flags occurrences of the copular verb “is” when it’s used to introduce a subject in definitional or topic-statement sentences.

    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
     that
    -2.69
     with
    -2.69
     one
    -2.28
     from
    -2.02
     this
    -1.98
     and
    -1.97
     as
    -1.94
     until
    -1.92
     other
    -1.88
     (
    -1.78
    POSITIVE LOGITS
     我们
    1.66
    ³,
    1.59
     recordó
    1.56
     consulte
    1.55
    我们的
    1.52
     relâche
    1.51
    𒊹
    1.47
    ᨆ
    1.45
     maquilla
    1.44
     ceremonia
    1.44
    Activations Density 0.395%

    No Known Activations