© 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. 101652
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    whitespace indentation at the beginning of lines in source code files.

    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
     vêtements
    -1.45
    ージョン
    -1.45
     sais
    -1.41
    numericUpDown
    -1.38
     waarschijnlijk
    -1.34
     hebben
    -1.34
     梁
    -1.33
     КУ
    -1.33
     jouets
    -1.33
     tailles
    -1.33
    POSITIVE LOGITS
     to
    2.02
     so
    1.63
     this
    1.56
     using
    1.54
     it
    1.50
     see
    1.45
    {
    1.40
     in
    1.39
     everything
    1.37
     one
    1.36
    Activations Density 0.353%

    No Known Activations