© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116610
    Prev
    Next
    INDEX
    Explanations

    specific calculation results

    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
     THREE
    -0.06
     three
    -0.06
     మూడు
    -0.06
    それが
    -0.06
     by
    -0.06
     bonnes
    -0.06
     Buenas
    -0.06
    jack
    -0.06
     categoryService
    -0.06
     باعث
    -0.06
    POSITIVE LOGITS
     selber
    0.06
     ежеднев
    0.06
     från
    0.06
     yani
    0.06
     standalone
    0.06
     இரா
    0.06
     immigrant
    0.06
     täglich
    0.06
     平
    0.05
    ő
    0.05
    Activations Density 0.003%

    No Known Activations