© 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. 117698
    Prev
    Next
    INDEX
    Explanations

    numbers following specific tokens

    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
     พูด
    -0.06
     Nutzen
    -0.06
     उभार
    -0.06
    พูด
    -0.06
     sausages
    -0.06
    信用
    -0.06
     stro
    -0.06
     मनोहर
    -0.06
     چند
    -0.06
    뜬
    -0.06
    POSITIVE LOGITS
     দ্বিতীয়
    0.06
    Otra
    0.06
     соблю
    0.06
     other
    0.06
    lehem
    0.06
     তৃতীয়
    0.06
     Territorial
    0.06
     সম্পাদকীয়
    0.06
     Gim
    0.06
     altri
    0.05
    Activations Density 0.004%

    No Known Activations