© 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-65K
    7. 52340
    Prev
    Next
    INDEX
    Explanations

    deliberately casual tone

    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_65k_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
     struggles
    0.53
     desperate
    0.48
     desperately
    0.48
    Attempt
    0.47
    끙
    0.47
     anxious
    0.46
     Attempt
    0.46
     dû
    0.46
     struggled
    0.46
     Strugg
    0.46
    POSITIVE LOGITS
     smirk
    0.89
     mocking
    0.88
     smug
    0.80
    嘲
    0.80
     mockery
    0.80
     mischiev
    0.78
     teasing
    0.77
     provoc
    0.72
     sarcastic
    0.71
     mocks
    0.71
    Activations Density 0.141%

    No Known Activations