© 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. 128319
    Prev
    Next
    INDEX
    Explanations

    new model

    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
    类型的
    -0.06
    jdk
    -0.06
     characterizes
    -0.06
     यौन
    -0.06
    🛸
    -0.06
     cephal
    -0.06
     also
    -0.06
     spraw
    -0.06
    চীনের
    -0.06
     CMD
    -0.06
    POSITIVE LOGITS
     উন্নয়ন
    0.06
     осна
    0.06
    ម
    0.06
     പക
    0.06
    新款
    0.06
     Colle
    0.05
     опас
    0.05
    ෝ
    0.05
    using
    0.05
     даже
    0.05
    Activations Density 0.026%

    No Known Activations