© 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. 129643
    Prev
    Next
    INDEX
    Explanations

    xsd or dtd schemas

    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
    र्यंत
    -0.07
     sebi
    -0.06
    專家
    -0.06
    kee
    -0.06
    Տ
    -0.06
     amounted
    -0.06
     zwy
    -0.06
    を楽しむ
    -0.06
     swell
    -0.06
    ेंशन
    -0.06
    POSITIVE LOGITS
    आख
    0.06
     this
    0.06
     generation
    0.06
     आखिर
    0.06
     گوش
    0.06
     সময়ের
    0.06
     наконец
    0.06
     오늘도
    0.06
    谒
    0.06
     чуть
    0.06
    Activations Density 0.001%

    No Known Activations