© 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. 70547
    Prev
    Next
    INDEX
    Explanations

    reporting speech

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

    The neuron strongly activates on the reporting verb “saying.”

    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
    綽
    -2.83
    
    -2.70
    breviations
    -2.59
    romas
    -2.59
    驛
    -2.47
     habido
    -2.41
    を
    -2.39
    ל
    -2.36
    tividade
    -2.36
     took
    -2.36
    POSITIVE LOGITS
    を変える
    2.70
     plausible
    2.61
     любого
    2.53
     tätig
    2.53
    the
    2.52
    摸了
    2.52
    倏
    2.41
     entrando
    2.34
     Of
    2.33
     probable
    2.33
    Activations Density 0.004%

    No Known Activations