© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 64990
    Prev
    Next
    INDEX
    Explanations

    reporting speech

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

    This neuron detects occurrences of the reporting verb “said,” i.e. attribution of quoted or reported speech.

    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
     noastre
    -1.57
     empez
    -1.52
     duradero
    -1.51
     rompi
    -1.49
    corpion
    -1.47
     französische
    -1.46
     "
    -1.44
     estadounidenses
    -1.43
    などなど
    -1.38
     navideño
    -1.35
    POSITIVE LOGITS
     the
    2.59
     Oleh
    1.58
    -------------
    1.53
     hatt
    1.42
     milliard
    1.41
     psychiat
    1.38
     炖
    1.38
    ੲ
    1.38
    vég
    1.34
     rechange
    1.33
    Activations Density 0.009%

    No Known Activations