© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119762
    Prev
    Next
    INDEX
    Explanations

    measurements and following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     सुनना
    -0.07
    嫉
    -0.06
     sc
    -0.06
     цієї
    -0.06
    इयों
    -0.06
     weiterer
    -0.06
                       
    -0.05
                        
    -0.05
    Gc
    -0.05
     CF
    -0.05
    POSITIVE LOGITS
     เป็น
    0.08
     είναι
    0.07
     कोई
    0.07
    leta
    0.06
     nào
    0.06
     là
    0.06
     是
    0.06
     bibliography
    0.06
     żad
    0.06
     কোন
    0.06
    Activations Density 0.001%

    No Known Activations