© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72793
    Prev
    Next
    INDEX
    Explanations

    attorney general texas

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

    This neuron detects document header metadata—uppercase headings, court names, dates, and other all-caps labels and numbers at the top of legal or formal documents.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -1.32
     had
    -1.20
     six
    -1.18
     from
    -1.17
     eight
    -1.11
     all
    -1.08
     or
    -1.06
     took
    -1.05
     while
    -1.04
     sucedido
    -1.02
    POSITIVE LOGITS
    你的
    1.16
     achet
    1.05
    LOS
    1.03
     tivi
    1.03
    +:+
    1.02
     senza
    1.02
     começa
    1.02
     pensare
    1.02
    __(/*!
    1.01
     wanders
    1.01
    Activations Density 0.025%

    No Known Activations