© 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. 120277
    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
    고
    -0.06
    라는
    -0.06
    निम्
    -0.06
    쨍
    -0.06
    ਕਾਰੀ
    -0.06
     พิจิก
    -0.05
     disini
    -0.05
    स्ट
    -0.05
    াপন্ন
    -0.05
    텅
    -0.05
    POSITIVE LOGITS
     Traditional
    0.06
     but
    0.06
     But
    0.06
     traditional
    0.06
     K
    0.06
     from
    0.06
     when
    0.06
     জিজ্ঞাসাবাদ
    0.06
    既に
    0.06
    But
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.