© 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. 259
    Prev
    Next
    INDEX
    Explanations

    code syntax and types

    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
     and
    -1.13
     sprung
    -0.80
    illige
    -0.78
    趣
    -0.78
    瑋
    -0.75
    ρί
    -0.73
    かげ
    -0.73
     purcha
    -0.72
    닛
    -0.71
     Extraordinary
    -0.71
    POSITIVE LOGITS
    ?[
    1.08
    Sicherheit
    0.98
    桕
    0.95
     beban
    0.94
    Nueva
    0.94
    Erfahrung
    0.93
    ISSIPPI
    0.90
    Haven
    0.89
     reç
    0.88
    Activator
    0.87
    Activations Density 0.003%

    No Known Activations