© 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. 9629
    Prev
    Next
    INDEX
    Explanations

    json fields or code structures

    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
    ﻹ
    -1.16
     mengucapkan
    -1.06
     accesorios
    -0.99
    ęż
    -0.99
     deklar
    -0.97
     avulla
    -0.97
    InBackground
    -0.96
     PREVIOUS
    -0.95
     antiguos
    -0.94
    فية
    -0.94
    POSITIVE LOGITS
    قرأ
    0.85
    шных
    0.85
    ITHER
    0.85
    是個
    0.84
    ”
    0.84
     aligned
    0.82
     卒業
    0.81
    (!)
    0.81
     there
    0.80
     both
    0.80
    Activations Density 0.000%

    No Known Activations