© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129931
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    羯
    -0.07
     choć
    -0.06
    คนที่
    -0.06
     عاش
    -0.06
    すでに
    -0.06
    已经是
    -0.06
    已经在
    -0.06
    后续
    -0.06
     देत
    -0.06
     dettagli
    -0.06
    POSITIVE LOGITS
     möglicherweise
    0.07
     ônibus
    0.07
     along
    0.07
     TWO
    0.06
     econ
    0.06
    clos
    0.06
    tae
    0.06
     alongside
    0.06
     unbiased
    0.06
     utmost
    0.06
    Activations Density 0.008%

    No Known Activations