© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9252
    Prev
    Next
    INDEX
    Explanations

    titles of movies and books

    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
     feltro
    -1.91
    歺
    -1.85
     arriver
    -1.78
    
    -1.77
     inverno
    -1.75
    亊
    -1.74
     撮っ
    -1.73
    乁
    -1.73
    梿
    -1.71
    泐
    -1.71
    POSITIVE LOGITS
    :
    2.41
     at
    2.36
     in
    2.36
    -
    1.95
     For
    1.95
     if
    1.91
     In
    1.91
     so
    1.91
     just
    1.88
     Even
    1.87
    Activations Density 0.084%

    No Known Activations