© 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. 129119
    Prev
    Next
    INDEX
    Explanations

    common factor or multiple

    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
     an
    -0.08
     two
    -0.08
    ,..
    -0.07
    ,
    -0.07
     a
    -0.06
     खाम
    -0.06
     three
    -0.06
    include
    -0.06
    ,,
    -0.06
     multiple
    -0.06
    POSITIVE LOGITS
     τους
    0.06
     tất
    0.06
    없는
    0.06
     semua
    0.06
     maneiras
    0.06
     مثلا
    0.06
     അവരുടെ
    0.06
     might
    0.06
    ụp
    0.06
     desaparecido
    0.05
    Activations Density 0.023%

    No Known Activations