© 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. 117671
    Prev
    Next
    INDEX
    Explanations

    time related information

    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
     분명
    -0.06
     Porte
    -0.06
     expanding
    -0.06
     exclaimed
    -0.06
     २०१
    -0.05
    expanded
    -0.05
     ‘
    -0.05
    ง่าย
    -0.05
     ’
    -0.05
     Mal
    -0.05
    POSITIVE LOGITS
     ваша
    0.07
     propietario
    0.06
     Vettel
    0.06
     дві
    0.06
    Silence
    0.06
     ориги
    0.06
     guerre
    0.06
     your
    0.06
     질문
    0.06
     yarat
    0.06
    Activations Density 0.003%

    No Known Activations