© 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. 120916
    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
    Negative Logits
     također
    -0.07
     amalgamation
    -0.06
     Advisors
    -0.06
    lamydia
    -0.06
     xong
    -0.06
     също
    -0.06
    োয়া
    -0.06
     advisors
    -0.06
     bestowed
    -0.06
     appointees
    -0.06
    POSITIVE LOGITS
     प्रक्षे
    0.06
    ELECTRON
    0.06
     Jake
    0.06
     Phone
    0.06
     Coch
    0.06
     olduğu
    0.06
    __).
    0.06
    போது
    0.05
     기대
    0.05
     صوب
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.