© 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. 118041
    Prev
    Next
    INDEX
    Explanations

    family:, Q:, Effect of

    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
     غم
    -0.07
     ช่วย
    -0.07
    Gö
    -0.06
    Easing
    -0.06
     요
    -0.06
    내가
    -0.06
    陴
    -0.06
     particolarmente
    -0.06
     nessun
    -0.06
    Helping
    -0.06
    POSITIVE LOGITS
    和
    0.06
    titleTextStyle
    0.06
     প্রবৃত্ত
    0.05
     EXP
    0.05
     Ihrer
    0.05
     동안
    0.05
     ابتد
    0.05
    磅
    0.05
    推奨
    0.05
     SJ
    0.05
    Activations Density 0.001%

    No Known Activations