© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16571
    Prev
    Next
    INDEX
    Explanations

    division or department

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

    The neuron activates on formal court‐name designations (e.g. “Court of Appeal,” “Appellate Division,” “Federal Circuit,” etc.).

    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
     by
    -1.55
     our
    -1.52
     any
    -1.45
     their
    -1.37
     this
    -1.30
     July
    -1.23
     new
    -1.15
     October
    -1.14
     hacían
    -1.13
     first
    -1.13
    POSITIVE LOGITS
    such
    1.20
     inscripción
    1.20
    Passer
    1.19
     recomendación
    1.16
    hradun
    1.15
     delegación
    1.13
    腭
    1.13
    unków
    1.13
    توضیحات
    1.13
     SUCH
    1.12
    Activations Density 0.002%

    No Known Activations