© 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. 22-GEMMASCOPE-RES-131K
    7. 129068
    Prev
    Next
    INDEX
    Explanations

    configuration and code structure

    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_22/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
    みてください
    -1.02
     frecuentes
    -1.02
    aliers
    -1.00
    addafi
    -0.99
     recientes
    -0.97
    licability
    -0.97
     devido
    -0.97
     ];
    -0.95
     femenina
    -0.95
    ONLY
    -0.93
    POSITIVE LOGITS
    ,
    1.20
     Кубка
    1.05
     before
    1.04
    номер
    1.02
     الإلكتر
    0.96
     neki
    0.95
    Tils
    0.93
    run
    0.92
    篆
    0.92
    omaly
    0.91
    Activations Density 0.002%

    No Known Activations