© 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. 117729
    Prev
    Next
    INDEX
    Explanations

    discrete signals or systems

    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
     einzelnen
    -0.08
     sabe
    -0.07
    కరించ
    -0.07
     Yeah
    -0.06
     отдельных
    -0.06
    nah
    -0.06
     yeah
    -0.06
     jednotliv
    -0.06
     primarily
    -0.06
     foie
    -0.06
    POSITIVE LOGITS
    領
    0.07
     Canberra
    0.06
     aurora
    0.06
    ◎
    0.06
     পছন্দের
    0.06
    planet
    0.05
     bela
    0.05
    合法
    0.05
     समझौता
    0.05
    World
    0.05
    Activations Density 0.005%

    No Known Activations