© 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. 120491
    Prev
    Next
    INDEX
    Explanations

    many or multiple

    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
     related
    -0.08
     relacionados
    -0.07
     insbesondere
    -0.06
    íng
    -0.06
    related
    -0.06
     المتع
    -0.06
     relacionado
    -0.06
    ولات
    -0.06
     relating
    -0.06
     любых
    -0.06
    POSITIVE LOGITS
    两种
    0.07
    許多
    0.07
    多くの
    0.07
     สำหรับ
    0.07
     számos
    0.07
    三种
    0.07
     many
    0.07
     muchos
    0.07
    更多
    0.07
     ብዙ
    0.07
    Activations Density 0.005%

    No Known Activations