© 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. 130057
    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
     agus
    -0.06
    ⦖
    -0.06
    धीश
    -0.06
    щих
    -0.06
     Total
    -0.06
     sesuatu
    -0.05
    ENSOR
    -0.05
     sortes
    -0.05
     denominations
    -0.05
    сных
    -0.05
    POSITIVE LOGITS
     caught
    0.08
    caught
    0.07
     идти
    0.06
    緞
    0.06
    :
    0.06
     Caught
    0.06
     बेस्ड
    0.06
    珑
    0.06
    Caught
    0.06
    trying
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.