© 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. 22-GEMMASCOPE-RES-131K
    4. 79922
    Prev
    Next
    INDEX
    Explanations

    verbs for reporting speech

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

    This neuron spotlights reporting or attribution verbs (like “said”) that introduce quoted 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_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
     and
    -2.30
     which
    -1.78
     find
    -1.62
     of
    -1.58
     for
    -1.50
     who
    -1.49
     did
    -1.42
     not
    -1.42
     make
    -1.41
    ykjav
    -1.40
    POSITIVE LOGITS
     réve
    1.57
     花朵
    1.48
     europé
    1.45
     område
    1.44
     唯美
    1.44
     油画
    1.43
    Ꮚ
    1.43
     camiset
    1.43
     farine
    1.42
     légumes
    1.41
    Activations Density 0.012%

    No Known Activations