© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130149
    Prev
    Next
    INDEX
    Explanations

    urls and license text

    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
     you
    -0.08
    るので
    -0.07
     নিত্য
    -0.07
     insecurities
    -0.07
     will
    -0.06
     differentiates
    -0.06
     ])
    -0.06
    いつも
    -0.06
     interconnect
    -0.06
     പ്രതി
    -0.06
    POSITIVE LOGITS
     этот
    0.08
    这个
    0.08
     как
    0.07
     dette
    0.07
     какой
    0.07
     dando
    0.07
     какая
    0.07
    С
    0.06
    这
    0.06
    ීමේ
    0.06
    Activations Density 0.034%

    No Known Activations