© 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. 117567
    Prev
    Next
    INDEX
    Explanations

    Baltics

    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
    ळ्यात
    -0.07
     cuz
    -0.07
     wäre
    -0.06
     количество
    -0.06
     schwier
    -0.06
    マンション
    -0.06
    ＋
    -0.06
     wait
    -0.06
     unsol
    -0.06
    =((
    -0.06
    POSITIVE LOGITS
    )
    0.06
    entire
    0.06
     samot
    0.05
     samego
    0.05
    吸引
    0.05
    inject
    0.05
     jednak
    0.05
    -
    0.05
    쫙
    0.05
     एकदा
    0.05
    Activations Density 0.007%

    No Known Activations