© 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. 119586
    Prev
    Next
    INDEX
    Explanations

    structure of background

    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
     chọn
    -0.06
     произо
    -0.06
     внутри
    -0.06
     manchmal
    -0.06
    আমার
    -0.06
     ventilation
    -0.06
     aritm
    -0.06
     கட்டுமான
    -0.06
    ணய
    -0.06
     during
    -0.06
    POSITIVE LOGITS
     sunset
    0.06
    пен
    0.06
     سرطان
    0.06
     carriers
    0.06
    asov
    0.06
    Nya
    0.06
    frast
    0.06
    inspect
    0.06
     revolutionized
    0.06
     trends
    0.06
    Activations Density 0.001%

    No Known Activations