© 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. 119211
    Prev
    Next
    INDEX
    Explanations

    tests and assessments

    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
     heps
    -0.07
    Danke
    -0.06
    他們
    -0.06
     podían
    -0.06
     видел
    -0.06
     conceito
    -0.06
     ellos
    -0.06
     நினைவு
    -0.06
     busiest
    -0.06
     mlad
    -0.06
    POSITIVE LOGITS
     classify
    0.07
     तयारी
    0.06
     determining
    0.06
    determ
    0.06
    自分の
    0.06
    computer
    0.06
     classifying
    0.06
    म्मे
    0.06
    Computer
    0.06
    程度
    0.06
    Activations Density 0.008%

    No Known Activations