© 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. 34-GEMMASCOPE-RES-131K
    7. 79532
    Prev
    Next
    INDEX
    Explanations

    fake news and misinformation

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

    The neuron overwhelmingly activates on mentions of “fake news” and closely related information‐literacy and misinformation terms.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Archivado
    -0.89
    🏀
    -0.88
    沪
    -0.84
    Postcode
    -0.84
    │
    -0.84
     समीक्षा
    -0.81
    Aqu
    -0.80
     Signatures
    -0.80
     smuggling
    -0.80
     anderen
    -0.80
    POSITIVE LOGITS
     fake
    1.68
     misinformation
    1.57
     false
    1.34
     Fake
    1.34
     Facts
    1.31
     truth
    1.31
     disinformation
    1.30
     trusted
    1.30
     Fact
    1.27
     fact
    1.27
    Activations Density 0.035%

    No Known Activations