© 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. 129545
    Prev
    Next
    INDEX
    Explanations

    accession numbers or submission

    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
     अधिक
    -0.06
    谣
    -0.06
     онлайн
    -0.06
     genetics
    -0.06
    謠
    -0.06
     मुख्य
    -0.06
     directement
    -0.06
    ・・・
    -0.06
     encarg
    -0.06
     hacia
    -0.06
    POSITIVE LOGITS
     Prozess
    0.06
    弜
    0.06
     Prozesse
    0.06
    䄱
    0.06
    䧺
    0.06
    臤
    0.06
    䄸
    0.06
     intricacies
    0.06
    proces
    0.06
    sproz
    0.06
    Activations Density 0.003%

    No Known Activations