© 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. 84760
    Prev
    Next
    INDEX
    Explanations

    contempt of court

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

    The neuron spotlights formal legal terminology around contempt proceedings—especially phrases like “contempt of court.”

    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
    ⎆
    -1.58
    そういえば
    -1.48
     kombat
    -1.47
    ✴
    -1.44
     tradis
    -1.38
    Making
    -1.36
     who
    -1.34
    Reminder
    -1.34
    Dentro
    -1.34
    mismo
    -1.33
    POSITIVE LOGITS
    </sup>
    1.55
     and
    1.45
    </b>
    1.38
     in
    1.34
     innovation
    1.32
    ="
    1.24
     podremos
    1.23
     Unglück
    1.23
     Menschheit
    1.22
     or
    1.16
    Activations Density 0.034%

    No Known Activations