© 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. 103464
    Prev
    Next
    INDEX
    Explanations

    called, is definitional

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

    The neuron fires on definitional copula phrases, in particular the pattern “is a” introducing definitions.

    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
     itali
    -1.51
     dras
    -1.46
     barres
    -1.42
     italiens
    -1.41
    WITHOUT
    -1.41
     colonnes
    -1.39
     TÉ
    -1.38
    twenty
    -1.37
    ŕ
    -1.36
     UNIVERS
    -1.35
    POSITIVE LOGITS
     should
    2.22
     any
    1.97
     or
    1.84
     such
    1.83
     called
    1.80
     an
    1.68
     this
    1.66
     including
    1.66
     in
    1.65
     of
    1.64
    Activations Density 0.079%

    No Known Activations