© 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. 128337
    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
     bless
    -0.07
     into
    -0.06
     nigh
    -0.06
     Blessing
    -0.06
     enhance
    -0.06
    更に
    -0.06
    Bless
    -0.06
    ・・・・
    -0.06
    ப்பதற்கு
    -0.06
    还要
    -0.06
    POSITIVE LOGITS
     algunas
    0.06
     ಇತರ
    0.06
     przewod
    0.06
     अन्य
    0.06
     other
    0.06
    Any
    0.06
    similar
    0.06
     esclusivamente
    0.06
     supremacy
    0.06
    人気
    0.06
    Activations Density 0.000%

    No Known Activations