© 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. 116301
    Prev
    Next
    INDEX
    Explanations

    language governing

    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
     строи
    -0.07
     জাপ
    -0.07
     ainult
    -0.07
    のみ
    -0.06
    :][
    -0.06
     Mijn
    -0.06
     прозра
    -0.06
    мою
    -0.06
     niemie
    -0.06
    alabel
    -0.06
    POSITIVE LOGITS
    大多
    0.06
     conversation
    0.06
     meisten
    0.06
     usually
    0.06
     दोन्ही
    0.06
     convers
    0.06
     বেশিরভাগ
    0.06
    若干
    0.06
    提供
    0.06
    versorgung
    0.06
    Activations Density 0.001%

    No Known Activations