© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81270
    Prev
    Next
    INDEX
    Explanations

    end of quote followed by speech verbs

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

    This neuron detects dialogue attribution—instances of quoted speech together with the accompanying tag (e.g. “,” said, “?” asked, “,” he hissed, “,” growled, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    问道
    -1.18
     OGSÅ
    -1.05
     Fragen
    -1.00
    に行く
    -1.00
     هذه
    -0.98
     Así
    -0.96
     này
    -0.94
     هذا
    -0.94
    \[
    
    -0.93
     primeiro
    -0.91
    POSITIVE LOGITS
     came
    1.25
     comes
    1.09
    Fá
    1.08
    issements
    1.07
     prêtre
    1.06
     said
    1.05
     they
    1.04
    Raúl
    1.03
    Frédéric
    0.98
    Samedi
    0.93
    Activations Density 0.003%

    No Known Activations