© 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. 127426
    Prev
    Next
    INDEX
    Explanations

    variable names in API routes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    絝
    -1.56
    ꙰
    -1.54
    ܆
    -1.52
    
    -1.51
    ":[{
    -1.48
    ToolStripButton
    -1.46
    谢谢你
    -1.45
     nemlig
    -1.38
    ༅
    -1.36
     maat
    -1.34
    POSITIVE LOGITS
     of
    2.11
     for
    1.63
    ing
    1.62
    
    1.41
    \
    1.36
    After
    1.33
    ar
    1.32
     you
    1.32
    after
    1.31
    ueroa
    1.31
    Activations Density 0.005%

    No Known Activations