© 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. 129353
    Prev
    Next
    INDEX
    Explanations

    f =

    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
     the
    -0.06
     all
    -0.06
    yp
    -0.05
    ela
    -0.05
    filepath
    -0.05
     всей
    -0.05
     असल्या
    -0.05
    enfants
    -0.05
    每年
    -0.05
     எல்லா
    -0.05
    POSITIVE LOGITS
     forehead
    0.07
     disregarding
    0.07
     우리는
    0.06
     최대한
    0.06
     mūsų
    0.06
     علاقه
    0.06
     detay
    0.06
    詢
    0.06
     vårt
    0.06
     typographical
    0.06
    Activations Density 0.007%

    No Known Activations