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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 27870
    Prev
    Next
    INDEX
    Explanations

    liability and insurance coverage

    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_16_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
     Bén
    0.57
     buenos
    0.57
     Í
    0.57
     neuen
    0.56
     volvió
    0.56
     revitalization
    0.56
     Эта
    0.55
     novo
    0.55
     変
    0.55
    */}
    0.55
    POSITIVE LOGITS
     liability
    1.02
     insurance
    0.87
    Liability
    0.86
     Liability
    0.77
    Insurance
    0.76
    liability
    0.72
    保险
    0.70
     Insurance
    0.68
     culpable
    0.68
     liable
    0.67
    Activations Density 0.028%

    No Known Activations