© 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. 119857
    Prev
    Next
    INDEX
    Explanations

    sequence starters

    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
     smaller
    -0.06
     важных
    -0.06
     nexus
    -0.06
     சிகிச்ச
    -0.06
     rationale
    -0.06
    დი
    -0.06
    相等
    -0.06
     specialized
    -0.06
    旅遊
    -0.06
     visualization
    -0.06
    POSITIVE LOGITS
     ताकि
    0.06
     अम्
    0.06
    มาตรฐาน
    0.06
     щоб
    0.06
     রাত
    0.05
     Candidates
    0.05
     unduly
    0.05
    就是
    0.05
    噜
    0.05
     sufficiently
    0.05
    Activations Density 0.001%

    No Known Activations