© 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. 119435
    Prev
    Next
    INDEX
    Explanations

    symbols and foreign words

    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
     accomplishing
    -0.06
    शिवम
    -0.06
     creating
    -0.06
     achieve
    -0.06
     actually
    -0.05
     speculators
    -0.05
     মহিলার
    -0.05
     rupiah
    -0.05
     optimistic
    -0.05
     Medvedev
    -0.05
    POSITIVE LOGITS
     réduction
    0.07
     dobrze
    0.07
     Protein
    0.07
     един
    0.07
     Ihren
    0.07
     диф
    0.06
     három
    0.06
     nú
    0.06
     notamment
    0.06
     hade
    0.06
    Activations Density 0.001%

    No Known Activations