© 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. 36654
    Prev
    Next
    INDEX
    Explanations

    demonstrating or testing methods

    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
     Presentations
    -0.88
    選擇
    -0.88
    原因
    -0.88
    取决
    -0.87
     Helf
    -0.86
    begins
    -0.86
     entiende
    -0.85
    选择
    -0.85
    flä
    -0.84
     cintas
    -0.83
    POSITIVE LOGITS
     tested
    1.46
     results
    1.37
     test
    1.30
     resulting
    1.23
     successfully
    1.23
    Tested
    1.13
     proved
    1.12
     preliminary
    1.04
     tests
    1.02
     pilot
    1.02
    Activations Density 0.203%

    No Known Activations