© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 14527
    Prev
    Next
    INDEX
    Explanations

    XPath element selection

    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
    磴
    0.40
    瞑
    0.39
     뭐가
    0.38
     Bergh
    0.38
    質感
    0.38
     पाण
    0.37
    رمان
    0.37
     منف
    0.37
     दरबार
    0.36
     meningitis
    0.36
    POSITIVE LOGITS
    [@
    0.80
     [@
    0.75
     descendant
    0.74
    (@
    0.69
    *[
    0.65
     ancestor
    0.62
    ]/
    0.60
     XPath
    0.58
    ancest
    0.58
    ()[
    0.57
    Activations Density 0.005%

    No Known Activations