© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 119414
    Prev
    Next
    INDEX
    Explanations

    Bilderback, farm, cohort, Virginia, Prepared, Dipl

    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
    इयों
    -0.06
     čak
    -0.06
     sogar
    -0.06
     khoảng
    -0.06
    を経て
    -0.06
    栽培
    -0.05
    緑
    -0.05
    一致
    -0.05
     unprecedented
    -0.05
    業界
    -0.05
    POSITIVE LOGITS
     you
    0.08
    詳しい
    0.07
     You
    0.07
    检查
    0.06
    レポート
    0.06
    檢查
    0.06
    copies
    0.06
     உங்கள்
    0.06
     Knowledge
    0.06
    ിലോ
    0.06
    Activations Density 0.004%

    No Known Activations