© 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. 119440
    Prev
    Next
    INDEX
    Explanations

    code invocation and definition

    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
    ೃ
    -0.06
     ehemaligen
    -0.06
     Bukan
    -0.06
    第二个
    -0.06
     первом
    -0.06
     bicara
    -0.06
     рублей
    -0.06
     전
    -0.05
     isteyen
    -0.05
     what
    -0.05
    POSITIVE LOGITS
     भेज
    0.06
     बदलकर
    0.06
    クス
    0.06
    ísim
    0.06
     настолько
    0.06
     بهذه
    0.06
     utilizando
    0.05
    すぎて
    0.05
    atology
    0.05
     undoubtedly
    0.05
    Activations Density 0.002%

    No Known Activations