© 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. 194600
    Prev
    Next
    INDEX
    Explanations

    foreign words and SAP

    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
    AW
    0.37
     soliciting
    0.37
    Haha
    0.36
    짊
    0.35
    reetype
    0.34
     જોઈ
    0.34
    ﹡
    0.34
     భా
    0.34
    inairement
    0.34
     হ্রাস
    0.34
    POSITIVE LOGITS
     روی
    0.44
    基于
    0.43
     buat
    0.42
    uitse
    0.41
    对
    0.41
     относится
    0.40
     στην
    0.39
     untuk
    0.39
    برای
    0.39
     برای
    0.39
    Activations Density 0.000%

    No Known Activations