© 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. 10-GEMMASCOPE-RES-131K
    7. 67464
    Prev
    Next
    INDEX
    Explanations

    legal judgments

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

    The neuron consistently picks up on the appearance of the word “Judgment” (and its nearby heading tokens) in court‐document titles or section headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -2.34
    
    -2.22
    ?"
    -2.16
     he
    -2.16
    ଢ
    -2.14
     مرکز
    -2.14
    ⡪
    -2.14
     置物
    -2.08
    ꦸ
    -2.08
    萏
    -2.06
    POSITIVE LOGITS
    .
    3.30
    此外
    2.64
    ↵
    2.44
    虽说
    2.30
    In
    2.27
     that
    2.23
    If
    2.22
    总之
    2.19
    2.08
    </td>
    2.02
    Activations Density 0.010%
    No Known Activations