© 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. 50020
    Prev
    Next
    INDEX
    Explanations

    consecutive or adjacent items

    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
     GÉN
    0.43
    ႁ
    0.43
     രക്ഷ
    0.42
     avocat
    0.42
    栝
    0.42
     Đúng
    0.41
     MDET
    0.39
    മിതി
    0.39
     الوصول
    0.38
    抡
    0.38
    POSITIVE LOGITS
     consecutive
    0.86
     adjacent
    0.75
    adjacent
    0.73
     successive
    0.72
     연속
    0.71
    相邻
    0.71
     Consecutive
    0.69
    隣
    0.67
    Adjacent
    0.66
    連続
    0.65
    Activations Density 0.155%

    No Known Activations