© 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. 22-GEMMASCOPE-RES-131K
    7. 95641
    Prev
    Next
    INDEX
    Explanations

    documentation and source 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_22/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
     folosi
    -1.06
     usados
    -1.05
     usado
    -1.04
    fatt
    -1.03
    특
    -0.99
     cantit
    -0.98
     apó
    -0.95
     estudo
    -0.95
    .............
    -0.92
    すっ
    -0.92
    POSITIVE LOGITS
     of
    1.56
     where
    1.30
     to
    1.27
    家は
    1.13
     وكان
    1.12
     wherein
    1.05
    天神
    1.04
     regarding
    1.02
     again
    1.02
    complished
    1.02
    Activations Density 0.096%

    No Known Activations