© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116188
    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
    如何
    -0.06
     igual
    -0.06
    ✱
    -0.06
     &/
    -0.06
    依据
    -0.06
     როგორ
    -0.06
    islang
    -0.06
     honed
    -0.05
     proportional
    -0.05
    রণ
    -0.05
    POSITIVE LOGITS
     नोएडा
    0.06
     многочис
    0.06
     sehingga
    0.06
     способен
    0.06
     conspiring
    0.06
     bốn
    0.06
    彼は
    0.06
     ನಾಲ್
    0.06
    Rows
    0.06
    торое
    0.06
    Activations Density 0.000%

    No Known Activations