© 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. 10766
    Prev
    Next
    INDEX
    Explanations

    unexpected surprise

    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
    ेक्स
    0.43
    之为
    0.42
     concentrate
    0.41
    Roboto
    0.40
     quantifier
    0.40
     пыта
    0.39
    Infer
    0.38
    量
    0.38
    량을
    0.37
     संगम
    0.37
    POSITIVE LOGITS
     unexpected
    2.16
     surprising
    1.98
     неожидан
    1.98
    unexpected
    1.97
     inesper
    1.93
     Unexpected
    1.92
     surprise
    1.91
     unexpectedly
    1.86
     surprises
    1.85
    Unexpected
    1.84
    Activations Density 0.191%

    No Known Activations