© 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. 3533
    Prev
    Next
    INDEX
    Explanations

    United States Court of Appeals

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

    The neuron reliably fires on standalone all-caps header or label tokens (e.g. “FILED,” “PUBLICATION,” long uppercase words in a document’s heading).

    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
     did
    -1.12
    Obrázky
    -1.03
     after
    -1.01
     had
    -1.00
     could
    -0.94
     becomes
    -0.92
     found
    -0.92
     does
    -0.91
     Júnior
    -0.90
    جر
    -0.90
    POSITIVE LOGITS
     хочу
    1.14
     intrigu
    1.07
    avocat
    1.02
    regarding
    1.00
    wanted
    1.00
     tunik
    0.98
     EVEN
    0.96
     надпись
    0.95
    luss
    0.94
     DOING
    0.94
    Activations Density 0.000%

    No Known Activations