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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107665
    Prev
    Next
    INDEX
    Explanations

    establishing or proving claims

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

    The neuron detects the standard legal exception clause listing purposes (“establishing res judicata, collateral estoppel, or the law of the case”) for citing unpublished opinions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    cademic
    -1.01
    带来的
    -0.94
    umani
    -0.88
    还是很
    -0.87
     apparaît
    -0.86
    tika
    -0.86
     マウス
    -0.86
    visuel
    -0.84
     membuatnya
    -0.84
     podemos
    -0.82
    POSITIVE LOGITS
     lack
    1.41
     sufficient
    1.34
     compliance
    1.23
     adequate
    1.13
     absence
    1.05
     a
    1.05
     facts
    1.04
     continued
    1.03
    事実
    1.01
     existence
    1.00
    Activations Density 0.041%

    No Known Activations