© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99008
    Prev
    Next
    INDEX
    Explanations

    closing tags, licensed, caption

    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
     plafon
    -0.99
     DIEGO
    -0.98
     Архи
    -0.96
    Вариан
    -0.94
     japon
    -0.93
    делка
    -0.91
     hırka
    -0.91
     dévelo
    -0.91
    TRAVIS
    -0.91
    老头
    -0.90
    POSITIVE LOGITS
     <
    1.03
     </
    1.02
     up
    0.91
     If
    0.90
     will
    0.90
     you
    0.87
    ↵↵↵↵↵
    0.87
     this
    0.84
     if
    0.84
     said
    0.83
    Activations Density 0.011%

    No Known Activations