© 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. 89874
    Prev
    Next
    INDEX
    Explanations

    00-99

    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
     at
    -1.08
     auf
    -1.04
     so
    -0.96
     irrespective
    -0.94
     oh
    -0.93
     in
    -0.91
     has
    -0.91
     even
    -0.89
     what
    -0.88
     without
    -0.87
    POSITIVE LOGITS
     kürzlich
    1.08
     rodas
    1.04
     sombre
    0.99
     resul
    0.99
     vermelho
    0.97
     Mugh
    0.95
     rog
    0.95
    鶫
    0.94
     抠
    0.93
    illir
    0.92
    Activations Density 0.033%

    No Known Activations