© 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. 118941
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     우리는
    -0.06
    দর্শক
    -0.06
    我們
    -0.06
     like
    -0.06
     我們
    -0.06
     our
    -0.06
    我們要
    -0.06
    我们
    -0.06
     ہمارے
    -0.06
     NEWS
    -0.06
    POSITIVE LOGITS
     continuamente
    0.06
    codeInput
    0.06
     constantly
    0.06
     максимум
    0.06
     continually
    0.06
     עוד
    0.06
    damageCount
    0.06
     liberally
    0.06
     badly
    0.06
     fréquemment
    0.06
    Activations Density 0.000%

    No Known Activations