© 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. 130432
    Prev
    Next
    INDEX
    Explanations

    Honda, Nissan, Toyota

    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
     уже
    -0.07
     allerede
    -0.06
    再び
    -0.06
     pasting
    -0.06
    众多
    -0.06
    联邦
    -0.06
     nuovamente
    -0.06
     sensual
    -0.06
     competitivo
    -0.06
    nab
    -0.06
    POSITIVE LOGITS
    どちら
    0.06
    ichael
    0.06
     Umum
    0.06
     Hibernate
    0.06
     voir
    0.06
    dar
    0.06
    बन्ध
    0.06
     selle
    0.06
    être
    0.05
    とのこと
    0.05
    Activations Density 0.004%

    No Known Activations