© 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. 40733
    Prev
    Next
    INDEX
    Explanations

    is followed by description

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

    The neuron strongly lights up on copular “to be” forms (e.g. is, was).

    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
     industrie
    -2.03
     taxe
    -1.95
     curie
    -1.88
     notori
    -1.86
     cabine
    -1.79
    OOOO
    -1.77
     citer
    -1.77
     maxime
    -1.73
     brune
    -1.73
     cern
    -1.72
    POSITIVE LOGITS
     what
    2.44
     would
    2.27
     Why
    2.22
     probably
    2.14
     an
    1.92
     could
    1.92
     should
    1.88
     a
    1.86
     might
    1.84
     Would
    1.81
    Activations Density 0.116%

    No Known Activations