© 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. 117045
    Prev
    Next
    INDEX
    Explanations

    rights and amendments

    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
    取决于
    -0.07
    istit
    -0.07
    推荐
    -0.06
    RECOMM
    -0.06
    ोच्च
    -0.06
    祝
    -0.06
    推薦
    -0.06
     recomendar
    -0.06
    :
    -0.06
     рекоменда
    -0.05
    POSITIVE LOGITS
     ausführ
    0.07
    hello
    0.06
    ವೇಂದ್ರ
    0.06
     ámbitos
    0.06
    ewa
    0.06
     interactions
    0.06
     அப்பா
    0.06
     फिल्टर
    0.06
    日下午
    0.06
     जानने
    0.06
    Activations Density 0.001%

    No Known Activations