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

    Neuronpedia

    Jacobian LensNEW
    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. 54158
    Prev
    Next
    INDEX
    Explanations

    unexpectedness or 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
    बंग
    0.45
    ündung
    0.44
    ühm
    0.44
    埥
    0.44
    CodeDict
    0.44
    㡺
    0.44
    ندن
    0.41
     グリーン
    0.41
    頻
    0.41
    的大
    0.40
    POSITIVE LOGITS
    竟然
    0.76
    居然
    0.68
     こんな
    0.61
    こんな
    0.57
     STILL
    0.57
     unbelievably
    0.52
    竟
    0.51
     such
    0.50
     still
    0.50
     столь
    0.48
    Activations Density 0.071%

    No Known Activations