© 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. 130312
    Prev
    Next
    INDEX
    Explanations

    names indicating possession then location/relationorpossession and origin/relation

    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
     había
    -0.06
     όμως
    -0.06
     generalmente
    -0.06
     consequences
    -0.06
     ওই
    -0.06
     течение
    -0.06
     दिखे
    -0.06
     कपास
    -0.05
     conséquences
    -0.05
     ovom
    -0.05
    POSITIVE LOGITS
     wanneer
    0.08
     quando
    0.08
     when
    0.08
     lorsqu
    0.07
    quando
    0.07
     cuando
    0.07
     όταν
    0.07
     khi
    0.07
    when
    0.07
     ketika
    0.07
    Activations Density 0.043%

    No Known Activations