© 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. 21113
    Prev
    Next
    INDEX
    Explanations

    programming code keywords

    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
    </h2>
    -1.83
    tahui
    -1.55
     adesivo
    -1.53
    我们
    -1.52
     みんな
    -1.45
    It
    -1.43
    
    -1.41
    它
    -1.39
     всі
    -1.38
     電話
    -1.38
    POSITIVE LOGITS
     of
    1.92
    อื่น
    1.76
     '
    1.60
    しくない
    1.55
     was
    1.49
     for
    1.48
     part
    1.43
     still
    1.34
    ágenes
    1.31
    idase
    1.29
    Activations Density 0.060%

    No Known Activations