© 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. 106143
    Prev
    Next
    INDEX
    Explanations

    political comedians and news outlets

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

    The neuron detects prominent multiword proper‐name entities—especially names of people, TV shows, publications, and media events.

    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
     Genel
    -0.69
    Dea
    -0.69
    urban
    -0.67
    ǖ
    -0.66
     plural
    -0.66
    晖
    -0.65
    usst
    -0.64
    共同
    -0.64
    WES
    -0.64
     EVALUATION
    -0.63
    POSITIVE LOGITS
     satirical
    1.12
     Daily
    1.09
     Colbert
    1.04
    Daily
    1.02
     Jon
    0.93
     corresponded
    0.92
     correspondents
    0.88
     Comedy
    0.88
     Stewart
    0.84
    Stewart
    0.83
    Activations Density 0.035%

    No Known Activations