© 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. 119445
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
     dust
    -0.06
    Exposure
    -0.06
     gritty
    -0.06
    afil
    -0.06
     righteous
    -0.05
     venture
    -0.05
    ゾン
    -0.05
     passionate
    -0.05
    Within
    -0.05
    됩니다
    -0.05
    POSITIVE LOGITS
     άλλ
    0.07
     quinto
    0.07
     Pensacola
    0.07
     dacă
    0.06
     sabato
    0.06
     დიდი
    0.06
     электри
    0.06
    监控
    0.06
     भाषा
    0.06
    不要
    0.06
    Activations Density 0.002%

    No Known Activations