© 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. 129929
    Prev
    Next
    INDEX
    Explanations

    Copyright

    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
    :
    -0.06
     brinc
    -0.06
     বাড়ী
    -0.06
     :
    -0.06
     acestea
    -0.06
     local
    -0.05
     eux
    -0.05
     eles
    -0.05
     Mt
    -0.05
     trades
    -0.05
    POSITIVE LOGITS
    尽管
    0.08
    母親
    0.07
     njegov
    0.07
     वर्षों
    0.07
    although
    0.07
     ஐந்து
    0.06
     necessaria
    0.06
     jeho
    0.06
    要在
    0.06
    添加
    0.06
    Activations Density 0.002%

    No Known Activations