© 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. 10-GEMMASCOPE-RES-131K
    7. 72917
    Prev
    Next
    INDEX
    Explanations

    really not sure

    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_10/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
     рассказать
    -2.06
    的眼神
    -1.91
    ⬮
    -1.89
    atação
    -1.80
    ܃
    -1.75
    ⦊
    -1.73
     eventuell
    -1.70
    
    -1.70
    媖
    -1.69
     recev
    -1.65
    POSITIVE LOGITS
    '
    2.02
    ↵
    1.92
     
    1.84
     głównie
    1.81
    一个小
    1.69
    U
    1.69
     can
    1.68
    のは
    1.67
    ’
    1.64
     devrait
    1.62
    Activations Density 0.016%

    No Known Activations