© 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. 102341
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure

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

    HTML/CSS code and markup syntax, particularly opening tags and structural elements.

    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
     with
    -2.06
     or
    -1.99
     while
    -1.95
     without
    -1.92
     before
    -1.83
     either
    -1.76
     but
    -1.71
     time
    -1.57
     if
    -1.53
     described
    -1.52
    POSITIVE LOGITS
     tohoto
    1.81
     naszej
    1.74
    汌
    1.72
    っているので
    1.70
    kurtka
    1.70
     وكذلك
    1.69
     höl
    1.67
     suspendu
    1.62
    われ
    1.61
     เรา
    1.61
    Activations Density 0.027%

    No Known Activations