© 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. 119943
    Prev
    Next
    INDEX
    Explanations

    lines, Sixth, Q, Learning, Cont

    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
     When
    -0.06
     wprowad
    -0.06
     samt
    -0.06
    を感じ
    -0.06
     gouvernement
    -0.06
     recommends
    -0.06
    zw
    -0.06
    regierung
    -0.06
     is
    -0.06
     administração
    -0.06
    POSITIVE LOGITS
     источников
    0.07
     조사
    0.07
     profesión
    0.07
    🔎
    0.06
    基于
    0.06
     inconclusive
    0.06
     onslaught
    0.06
     документов
    0.06
     मंजूर
    0.06
     agreed
    0.06
    Activations Density 0.001%

    No Known Activations