© 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. 9575
    Prev
    Next
    INDEX
    Explanations

    journal or publisher names

    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
    -2.11
    Tiene
    -1.93
    COMO
    -1.88
    
    -1.86
    SÍ
    -1.84
     plie
    -1.84
    嵎
    -1.84
     relâche
    -1.82
     balení
    -1.78
     รุ่น
    -1.76
    POSITIVE LOGITS
     in
    3.13
     but
    2.88
     and
    2.83
     of
    2.72
     by
    2.47
     on
    2.45
     more
    2.31
     at
    2.25
    co
    2.16
     from
    2.16
    Activations Density 0.012%

    No Known Activations