© 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. 128347
    Prev
    Next
    INDEX
    Explanations

    comparative evaluation of outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     first
    -0.07
     první
    -0.07
    最初の
    -0.07
    mergeddata
    -0.06
     botched
    -0.06
    inados
    -0.06
     первого
    -0.06
     experiments
    -0.06
     eerste
    -0.06
     ट्रायल
    -0.06
    POSITIVE LOGITS
    保持
    0.07
    they
    0.06
    primary
    0.06
    but
    0.06
    false
    0.06
     maintain
    0.06
     maintains
    0.06
     maintaining
    0.05
     discour
    0.05
     preserving
    0.05
    Activations Density 0.004%

    No Known Activations