© 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. 119349
    Prev
    Next
    INDEX
    Explanations

    under the license

    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
    最后的
    -0.07
     NOS
    -0.06
     великолеп
    -0.06
     சிவப்பு
    -0.06
     bordo
    -0.06
     eski
    -0.06
     क्रीम
    -0.06
     द्वीप
    -0.06
    蓝色
    -0.06
     dla
    -0.06
    POSITIVE LOGITS
    mers
    0.06
     মিলে
    0.06
    ogas
    0.06
     আবির্ভাব
    0.06
     ooz
    0.06
     erupt
    0.06
     حتى
    0.05
     disagrees
    0.05
    orgement
    0.05
     even
    0.05
    Activations Density 0.004%

    No Known Activations