© 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. 64319
    Prev
    Next
    INDEX
    Explanations

    share link and permissions

    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
     व
    0.46
     उ
    0.46
     mode
    0.45
     செய்யப்படும்
    0.43
     (>
    0.41
     diken
    0.41
     by
    0.41
     зая
    0.41
     (
    0.41
     देयर
    0.41
    POSITIVE LOGITS
    튀
    0.52
     veřej
    0.51
    আমরা
    0.50
    ła
    0.49
    获得了
    0.48
    śmy
    0.47
    alai
    0.47
    ỡi
    0.47
     hiện
    0.47
     giardino
    0.46
    Activations Density 0.003%

    No Known Activations