© 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. 130328
    Prev
    Next
    INDEX
    Explanations

    under the

    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
     kemungkinan
    -0.07
     intras
    -0.06
    formance
    -0.06
     comercio
    -0.06
    だと思います
    -0.06
    noff
    -0.06
    effet
    -0.06
     ederek
    -0.05
     the
    -0.05
     US
    -0.05
    POSITIVE LOGITS
    を用いる
    0.07
    數量
    0.06
    大學
    0.06
     பல்கலை
    0.06
    రుగులు
    0.06
     ثلاثة
    0.06
     다섯
    0.06
     distinct
    0.06
     هذه
    0.06
     यदि
    0.06
    Activations Density 0.003%

    No Known Activations