© 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. 45569
    Prev
    Next
    INDEX
    Explanations

    tensorflow and tf code

    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
    Життєпис
    -0.87
     ourselves
    -0.83
    GALLERY
    -0.75
    Lx
    -0.73
    енные
    -0.73
    แต่
    -0.73
     breite
    -0.72
    FactoryBean
    -0.71
     Himself
    -0.71
     Myself
    -0.71
    POSITIVE LOGITS
    idf
    1.29
     resumen
    0.93
     BOOL
    0.83
     dziecka
    0.80
    ighter
    0.77
    ERRORS
    0.77
     Kü
    0.77
     cualquier
    0.76
    ができます
    0.76
    indexPath
    0.75
    Activations Density 0.008%

    No Known Activations