© 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. 129131
    Prev
    Next
    INDEX
    Explanations

    not working

    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
     многим
    -0.06
    是因为
    -0.06
     siehe
    -0.05
     Everyone
    -0.05
    airo
    -0.05
    非常
    -0.05
     spécial
    -0.05
     kişinin
    -0.05
    一人
    -0.05
    POSITIVE LOGITS
    造成的
    0.06
     будут
    0.06
     отношения
    0.06
    但是
    0.06
     ও
    0.06
     sekarang
    0.06
     evolving
    0.06
    ទំនាក់
    0.06
     electroneg
    0.06
     خواهند
    0.06
    Activations Density 0.163%

    No Known Activations