© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128425
    Prev
    Next
    INDEX
    Explanations

    role attributes and values

    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
     about
    -1.94
     they
    -1.92
     würden
    -1.54
     we
    -1.52
     Zuhause
    -1.50
    などを
    -1.46
    などが
    -1.42
    
    -1.41
     have
    -1.41
    </h5>
    -1.40
    POSITIVE LOGITS
    0
    1.85
    Основные
    1.62
    8
    1.61
    Banyak
    1.57
    6
    1.55
    This
    1.54
    Лечение
    1.53
     สอง
    1.52
    Seperti
    1.48
    ～
    1.48
    Activations Density 0.007%

    No Known Activations