© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6699
    Prev
    Next
    INDEX
    Explanations

    reporting a claim

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

    This neuron detects passive reporting constructions, especially phrases like “said to have,” “is said to,” or similar “said to …” reports.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    assertAll
    -1.73
     all
    -1.70
     все
    -1.67
    
    -1.67
     और
    -1.65
    what
    -1.57
     как
    -1.56
     what
    -1.55
     și
    -1.54
     évidence
    -1.52
    POSITIVE LOGITS
    ,“
    1.89
    “,
    1.75
    :“
    1.72
    ’;
    1.71
     …..
    1.69
     verschieden
    1.61
    痦
    1.57
    …’
    1.55
     BECAUSE
    1.54
     ‚
    1.52
    Activations Density 0.012%

    No Known Activations