© 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. 79313
    Prev
    Next
    INDEX
    Explanations

    president followed by a name

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

    The neuron activates on named entities—particularly titles (e.g. “President”) and personal names.

    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
    王国
    -0.98
    人大
    -0.81
     recombination
    -0.80
    eseen
    -0.79
     postcode
    -0.76
     granola
    -0.72
    tadiene
    -0.70
     éditions
    -0.70
    lops
    -0.70
    polyline
    -0.68
    POSITIVE LOGITS
     President
    2.70
     president
    2.55
    President
    2.41
     presidents
    2.02
    president
    2.02
     Presidents
    1.84
     PRESIDENT
    1.77
    总统
    1.74
     presidential
    1.68
     президент
    1.63
    Activations Density 0.056%

    No Known Activations