© 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. 116253
    Prev
    Next
    INDEX
    Explanations

    perjury and false statements

    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
     информацию
    -0.07
    資訊
    -0.06
     информация
    -0.06
    情報は
    -0.06
     정보를
    -0.06
     information
    -0.06
    elola
    -0.06
     Informationen
    -0.06
     informações
    -0.06
     informacje
    -0.06
    POSITIVE LOGITS
     výkon
    0.07
     больших
    0.07
     разных
    0.07
     duż
    0.06
     húmed
    0.06
     plusieurs
    0.06
    複数の
    0.06
     novelist
    0.06
     ແ
    0.06
     verschillende
    0.06
    Activations Density 0.001%

    No Known Activations