© 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. 119879
    Prev
    Next
    INDEX
    Explanations

    Chopin, jurist, century, Chapman, pedagogical

    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
     Европы
    -0.06
    ヨーロッパ
    -0.06
    acul
    -0.06
     bravely
    -0.06
     courageous
    -0.06
    회
    -0.06
     Europe
    -0.06
    રૂ
    -0.05
     cortes
    -0.05
    toml
    -0.05
    POSITIVE LOGITS
     জানুয়ার
    0.06
     conspicuously
    0.06
     monopol
    0.06
     understatement
    0.06
     older
    0.06
    вые
    0.06
     distint
    0.06
     within
    0.06
    从事
    0.06
    पिछले
    0.06
    Activations Density 0.018%

    No Known Activations