© 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. 117642
    Prev
    Next
    INDEX
    Explanations

    programming interfaces and Q&A

    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
     பெயர்
    -0.08
     பெயரை
    -0.08
    期限
    -0.07
     rych
    -0.07
    名稱
    -0.07
    目標
    -0.07
     provisions
    -0.07
    深夜
    -0.06
    工资
    -0.06
    ！？
    -0.06
    POSITIVE LOGITS
     kept
    0.05
     उद्यमियों
    0.05
     dilaksanakan
    0.05
    MOUSE
    0.05
     pollute
    0.05
    CEEDINGS
    0.05
     conducted
    0.05
    $$\
    0.05
     acted
    0.05
     постара
    0.05
    Activations Density 0.001%

    No Known Activations