© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130642
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Q:"

    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
     récent
    -0.07
     निकाली
    -0.06
     chyba
    -0.06
     ("[
    -0.06
     फ़र
    -0.06
     dikutip
    -0.06
     reciente
    -0.06
     declining
    -0.06
    ↵↵
    -0.05
     récente
    -0.05
    POSITIVE LOGITS
    Temperature
    0.06
     rispetto
    0.06
     ভেতরে
    0.06
     irish
    0.06
     ভারতবর্ষে
    0.06
     प्रेम
    0.06
    Unknown
    0.05
    ূলে
    0.05
     unbek
    0.05
     وقت
    0.05
    Activations Density 0.001%

    No Known Activations