© 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. 128656
    Prev
    Next
    INDEX
    Explanations

    custom data or flags

    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
    分鐘
    -0.07
     Reproduction
    -0.06
     المسا
    -0.06
     तंत्र
    -0.06
    រូប
    -0.06
    lini
    -0.06
    ％
    -0.06
     partecip
    -0.06
     Kommunikation
    -0.06
     Serviço
    -0.06
    POSITIVE LOGITS
    д
    0.06
     hermoso
    0.06
    勿
    0.06
     অধিকাংশই
    0.06
     doubtless
    0.05
     jeweil
    0.05
    laat
    0.05
     wiele
    0.05
     nichts
    0.05
     Jako
    0.05
    Activations Density 0.001%

    No Known Activations