© 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. 34-GEMMASCOPE-RES-131K
    7. 4200
    Prev
    Next
    INDEX
    Explanations

    referred to as

    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_34/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
     augusti
    -1.16
     nok
    -1.03
     ۱۱
    -0.92
     kalla
    -0.92
     légales
    -0.91
     saks
    -0.91
     kuv
    -0.90
     kome
    -0.89
    csrf
    -0.88
     информацию
    -0.88
    POSITIVE LOGITS
    <h2>
    1.01
     możemy
    0.96
     destinados
    0.94
     apariencia
    0.94
    Groet
    0.94
     graduación
    0.93
     כשה
    0.92
     zosta
    0.91
    ↵↵
    0.91
     séjours
    0.91
    Activations Density 0.001%

    No Known Activations