© 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. 22-GEMMASCOPE-RES-131K
    7. 32616
    Prev
    Next
    INDEX
    Explanations

    AP, internet, Missouri, MO

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

    The neuron detects newswire dateline and byline markers (e.g. the “(AP)” source tag, location-dash patterns, and similar attribution tokens).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    нами
    -1.02
     herbes
    -1.01
     flamme
    -0.93
    鉿
    -0.90
     همان
    -0.90
     génération
    -0.90
    һы
    -0.89
     anderson
    -0.89
     angelo
    -0.89
     Réunion
    -0.88
    POSITIVE LOGITS
     Missouri
    1.56
    Missouri
    1.27
     négy
    1.09
     deutlich
    1.05
     day
    1.05
     supersede
    0.98
    での
    0.98
     Lengkap
    0.97
     redaktion
    0.97
     MO
    0.95
    Activations Density 0.013%

    No Known Activations