© 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. 22-GEMMASCOPE-RES-131K
    7. 26903
    Prev
    Next
    INDEX
    Explanations

    text inside quotes

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

    This neuron detects the start of a quoted passage, firing on the opening quotation mark and the first few words that follow it.

    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
     would
    -2.42
     should
    -2.41
     will
    -2.23
     could
    -2.22
     on
    -2.14
     might
    -1.90
     if
    -1.90
     an
    -1.88
     in
    -1.81
     may
    -1.80
    POSITIVE LOGITS
    basically
    2.06
    primarily
    1.79
     😁
    1.79
    generally
    1.75
     présenter
    1.73
    mainly
    1.73
     rése
    1.73
     créer
    1.65
     résister
    1.64
    really
    1.63
    Activations Density 0.020%

    No Known Activations