© 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. 130386
    Prev
    Next
    INDEX
    Explanations

    percentage of total

    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
     Purpose
    -0.07
     নিঃসন্দে
    -0.06
     keseluruhan
    -0.06
     WHILE
    -0.06
     operates
    -0.06
     और
    -0.06
    整體
    -0.06
     propre
    -0.06
     incorporates
    -0.06
     encompasses
    -0.06
    POSITIVE LOGITS
     اولین
    0.07
     relatifs
    0.06
    santa
    0.06
     almost
    0.06
     restantes
    0.06
     certain
    0.05
    пара
    0.05
     others
    0.05
     зокрема
    0.05
     रिव्यू
    0.05
    Activations Density 0.003%

    No Known Activations