© 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. 120020
    Prev
    Next
    INDEX
    Explanations

    job titles and ranks

    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
     adesi
    -1.73
     nastro
    -1.57
     サイド
    -1.57
    !”
    -1.56
    
    -1.51
    饜
    -1.49
     laba
    -1.48
    
    -1.48
     autocollant
    -1.47
    ?”
    -1.45
    POSITIVE LOGITS
     of
    3.06
     it
    2.59
     through
    2.09
     will
    1.88
     before
    1.80
     from
    1.72
     for
    1.70
     until
    1.69
     without
    1.59
     into
    1.50
    Activations Density 0.086%

    No Known Activations