© 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. 127759
    Prev
    Next
    INDEX
    Explanations

    legal citations and opinions

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

    The neuron detects court‐document procedural filing language, in particular terms around motions and rehearing requests.

    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
    nością
    -1.41
    くちゃ
    -1.31
     terribly
    -1.28
    رأة
    -1.26
     vitally
    -1.23
    
    -1.23
    rmtree
    -1.19
    });
    -1.15
    zenio
    -1.15
     devastating
    -1.14
    POSITIVE LOGITS
     that
    1.57
     llevaron
    1.26
     uiteindelijk
    1.14
     wohnen
    1.12
     县
    1.10
     querían
    1.09
    这些
    1.09
     vervolgens
    1.08
     Bí
    1.06
     tenían
    1.05
    Activations Density 0.082%

    No Known Activations