© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20381
    Prev
    Next
    INDEX
    Explanations

    legal fines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assassinated
    0.48
     geopol
    0.47
    proteins
    0.47
     murderous
    0.46
    大規模
    0.46
     নৃশংস
    0.46
    権
    0.45
     asesin
    0.44
     assassin
    0.44
     glycoproteins
    0.43
    POSITIVE LOGITS
     fines
    0.88
     fined
    0.79
     misdemeanor
    0.73
     জরিমানা
    0.70
     штра
    0.68
    罚
    0.66
     जुर्मा
    0.64
     जुर्माना
    0.64
    罰
    0.58
     violation
    0.56
    Activations Density 0.026%

    No Known Activations