© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91854
    Prev
    Next
    INDEX
    Explanations

    factual dispute

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

    The neuron detects the standard legal boilerplate requiring “sufficient facts to permit the court to reasonably conclude” that a claim lacks reasonable factual support (i.e. summary-judgment or pleading-sufficiency language).

    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
    koper
    -0.83
     %#
    -0.80
    пта
    -0.79
     Préférences
    -0.76
     zéro
    -0.75
    coran
    -0.75
     álcool
    -0.75
     {:.
    -0.75
    alisis
    -0.73
     bored
    -0.71
    POSITIVE LOGITS
     genuine
    1.58
     dispute
    1.34
     Genuine
    1.28
    genuine
    1.28
    Genuine
    1.27
     disputed
    1.23
     fact
    1.19
    fact
    1.15
     issue
    1.12
     tri
    1.06
    Activations Density 0.019%

    No Known Activations