© 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. 128979
    Prev
    Next
    INDEX
    Explanations

    various list prefixes

    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
     prénom
    -0.07
     grumpy
    -0.07
    但是
    -0.06
    當然
    -0.06
     ಆದರೆ
    -0.06
    もちろん
    -0.06
    字母
    -0.06
     لكن
    -0.06
    榀
    -0.06
     nhưng
    -0.06
    POSITIVE LOGITS
     these
    0.08
    这些
    0.08
     эти
    0.07
     such
    0.07
    這些
    0.07
     இவை
    0.06
    first
    0.06
     they
    0.06
     böyle
    0.06
    these
    0.06
    Activations Density 0.007%

    No Known Activations