© 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. 41-GEMMASCOPE-2-RES-262K
    7. 1056
    Prev
    Next
    INDEX
    Explanations

    travel from Doha

    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_all/layer_41_width_262k_l0_big
    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
    iliency
    0.54
    榖
    0.54
     servicing
    0.54
    ปลี่ยน
    0.53
     resiliency
    0.52
     incrementar
    0.51
    眝
    0.50
     busses
    0.50
     nettement
    0.50
    দ্যাল
    0.49
    POSITIVE LOGITS
     Xia
    0.63
     ，
    0.57
    ｜
    0.57
     WeChat
    0.55
    Zhang
    0.54
     Jian
    0.53
     Xiao
    0.52
     Luo
    0.52
    Xia
    0.52
     丨
    0.51
    Activations Density 0.002%

    No Known Activations