© 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. 129382
    Prev
    Next
    INDEX
    Explanations

    as follows

    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
     and
    -0.06
    Encycl
    -0.06
     résoudre
    -0.06
     toekom
    -0.06
     lì
    -0.06
     oceanic
    -0.06
     marzo
    -0.06
     Não
    -0.06
    indicate
    -0.06
     tiga
    -0.06
    POSITIVE LOGITS
     그러나
    0.07
    ifat
    0.06
     prosper
    0.06
     Однако
    0.06
     모두
    0.06
     они
    0.06
     elkaar
    0.06
     അവർ
    0.06
     regres
    0.06
    等的
    0.06
    Activations Density 0.001%

    No Known Activations