© 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. 40-GEMMASCOPE-2-RES-262K
    7. 222687
    Prev
    Next
    INDEX
    Explanations

    delivery performance, integer

    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_40_width_262k_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
    skills
    0.45
    スタイル
    0.41
    ΟΥ
    0.40
    ))%>%
    0.39
    ﻰ
    0.38
     ملا
    0.38
    шив
    0.37
    amment
    0.37
     awoke
    0.37
    лень
    0.36
    POSITIVE LOGITS
     波
    0.42
     회사
    0.39
    ኼ
    0.39
     Introducing
    0.39
     Conver
    0.38
    字节
    0.38
    Gesellschaft
    0.37
     عال
    0.37
     ഇവിടെ
    0.37
     比
    0.36
    Activations Density 0.000%

    No Known Activations