© 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. 116696
    Prev
    Next
    INDEX
    Explanations

    years, categories, or specific items

    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
     něk
    -0.07
     ⭐
    -0.06
     এই
    -0.06
    本書
    -0.06
     هذا
    -0.06
     više
    -0.06
     exemplaires
    -0.06
    unti
    -0.06
     Merkez
    -0.06
     vẫn
    -0.06
    POSITIVE LOGITS
    specificity
    0.07
     året
    0.06
    uvre
    0.06
     historical
    0.06
     specificity
    0.06
    typically
    0.06
    pecific
    0.06
     specifically
    0.06
    歴史
    0.06
     typically
    0.06
    Activations Density 0.003%

    No Known Activations