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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11815
    Prev
    Next
    INDEX
    Explanations

    Struts, tapestry, Geb, page

    np_acts-logits-general · gemini-2.5-flash-lite

    references to web framework technologies, particularly Struts, and related class or component names in code and documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     because
    -2.08
     for
    -1.86
     as
    -1.77
     before
    -1.58
     only
    -1.56
     on
    -1.55
     until
    -1.55
     since
    -1.53
     especially
    -1.52
     or
    -1.52
    POSITIVE LOGITS
    嫉妒
    1.51
     araña
    1.48
    ובה
    1.45
     presque
    1.42
     layui
    1.40
     bliss
    1.39
     Caracter
    1.39
    LUCK
    1.38
     dependen
    1.38
     borboleta
    1.34
    Activations Density 0.011%

    No Known Activations