© 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. 118375
    Prev
    Next
    INDEX
    Explanations

    already happened

    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
     anybody
    -0.06
     relaxing
    -0.06
    avec
    -0.06
     you
    -0.06
     kand
    -0.05
    চিত
    -0.05
    艺术
    -0.05
     예술
    -0.05
    它们的
    -0.05
    TTL
    -0.05
    POSITIVE LOGITS
     Сейчас
    0.07
     Đấy
    0.07
    Сейчас
    0.07
    すでに
    0.07
    如同
    0.07
     allerede
    0.06
    Kode
    0.06
     definido
    0.06
     компания
    0.06
     уже
    0.06
    Activations Density 0.001%

    No Known Activations