© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4296
    Prev
    Next
    INDEX
    Explanations

    legal actions and claims

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

    The neuron identifies mentions of legal actions, especially class-action lawsuits and related litigation terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     convivial
    0.78
     Imam
    0.77
     Nota
    0.76
     コ
    0.73
     priori
    0.73
     Tagore
    0.72
    /
    0.71
     progn
    0.70
     devi
    0.70
     diurnal
    0.69
    POSITIVE LOGITS
     lawsuits
    1.33
     lawsuit
    1.31
     plaintiffs
    1.09
     suing
    1.09
     شکایت
    0.99
     Plaintiffs
    0.99
    訴
    0.89
     lawyers
    0.86
     sued
    0.86
     alleging
    0.84
    Activations Density 0.083%

    No Known Activations